YOLOv4论文.pdf

发布时间：2022-05-31 发布人：admin 分类：说明书资料大小：3.76M 资料格式：pdf 举报版权申诉

qq_23306647-12655549-4744300845400075920.pdf-第1页.png

第1页 / 共17页

qq_23306647-12655549-4744300845400075920.pdf-第2页.png

第2页 / 共17页

qq_23306647-12655549-4744300845400075920.pdf-第3页.png

第3页 / 共17页

qq_23306647-12655549-4744300845400075920.pdf-第4页.png

第4页 / 共17页

qq_23306647-12655549-4744300845400075920.pdf-第5页.png

第5页 / 共17页

qq_23306647-12655549-4744300845400075920.pdf-第6页.png

第6页 / 共17页

qq_23306647-12655549-4744300845400075920.pdf-第7页.png

第7页 / 共17页

qq_23306647-12655549-4744300845400075920.pdf-第8页.png

第8页 / 共17页

文本预览

YOLOv4: Optimal Speed and Accuracy of Object Detection Alexey Bochkovskiy∗ alexeyab84@gmail.com Chien-Yao Wang∗ Hong-Yuan Mark Liao Institute of Information Science Institute of Information Science Academia Sinica, Taiwan kinyiu@iis.sinica.edu.tw Academia Sinica, Taiwan liao@iis.sinica.edu.tw 0 2 0 2 r p A 3 2 ] V C . s c [ 1 v 4 3 9 0 1 . 4 0 0 2 : v i X r a Abstract There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justiﬁcation of the result, is re- quired. Some features operate on certain models exclusively and for certain problems exclusively, or only for small-scale datasets; while some features, such as batch-normalization and residual-connections, are applicable to the majority of models, tasks, and datasets. We assume that such universal features include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT) and Mish-activation. We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, and CIoU loss, and com- bine some of them to achieve state-of-the-art results: 43.5% AP (65.7% AP50) for the MS COCO dataset at a real- time speed of ∼65 FPS on Tesla V100. Source code is at https://github.com/AlexeyAB/darknet. 1. Introduction The majority of CNN-based object detectors are largely applicable only for recommendation systems. For example, searching for free parking spaces via urban video cameras is executed by slow accurate models, whereas car collision warning is related to fast inaccurate models. Improving the real-time object detector accuracy enables using them not only for hint generating recommendation systems, but also for stand-alone process management and human input reduction. Real-time object detector operation on conven- tional Graphics Processing Units (GPU) allows their mass usage at an affordable price. The most accurate modern neural networks do not operate in real time and require large number of GPUs for training with a large mini-batch-size. We address such problems through creating a CNN that op- erates in real-time on a conventional GPU, and for which training requires only one conventional GPU. Figure 1: Comparison of the proposed YOLOv4 and other state-of-the-art object detectors. YOLOv4 runs twice faster than EfﬁcientDet with comparable performance. Improves YOLOv3’s AP and FPS by 10% and 12%, respectively. The main goal of this work is designing a fast operating speed of an object detector in production systems and opti- mization for parallel computations, rather than the low com- putation volume theoretical indicator (BFLOP). We hope that the designed object can be easily trained and used. For example, anyone who uses a conventional GPU to train and test can achieve real-time, high quality, and convincing ob- ject detection results, as the YOLOv4 results shown in Fig- ure 1. Our contributions are summarized as follows: 1. We develope an efﬁcient and powerful object detection model. It makes everyone can use a 1080 Ti or 2080 Ti GPU to train a super fast and accurate object detector. 2. We verify the inﬂuence of state-of-the-art Bag-of- Freebies and Bag-of-Specials methods of object detec- tion during the detector training. 3. We modify state-of-the-art methods and make them more effecient and suitable for single GPU training, including CBN [89], PAN [49], SAM [85], etc. 1

Figure 2: Object detector. 2. Related work 2.1. Object detection models A modern detector is usually composed of two parts, a backbone which is pre-trained on ImageNet and a head which is used to predict classes and bounding boxes of ob- jects. For those detectors running on GPU platform, their backbone could be VGG [68], ResNet [26], ResNeXt [86], or DenseNet [30]. For those detectors running on CPU plat- form, their backbone could be SqueezeNet [31], MobileNet [28, 66, 27, 74], or ShufﬂeNet [97, 53]. As to the head part, it is usually categorized into two kinds, i.e., one-stage object detector and two-stage object detector. The most represen- tative two-stage object detector is the R-CNN [19] series, including fast R-CNN [18], faster R-CNN [64], R-FCN [9], and Libra R-CNN [58]. It is also possible to make a two- stage object detector an anchor-free object detector, such as RepPoints [87]. As for one-stage object detector, the most representative models are YOLO [61, 62, 63], SSD [50], and RetinaNet [45]. In recent years, anchor-free one-stage object detectors are developed. The detectors of this sort are CenterNet [13], CornerNet [37, 38], FCOS [78], etc. Object detectors developed in recent years often insert some lay- ers between backbone and head, and these layers are usu- ally used to collect feature maps from different stages. We can call it the neck of an object detector. Usually, a neck is composed of several bottom-up paths and several top- down paths. Networks equipped with this mechanism in- clude Feature Pyramid Network (FPN) [44], Path Aggrega- tion Network (PAN) [49], BiFPN [77], and NAS-FPN [17]. 2 In addition to the above models, some researchers put their emphasis on directly building a new backbone (DetNet [43], DetNAS [7]) or a new whole model (SpineNet [12], HitDe- tector [20]) for object detection. To sum up, an ordinary object detector is composed of several parts: • Input: Image, Patches, Image Pyramid • Backbones: VGG16 [68], ResNet-50 [26], SpineNet [12], EfﬁcientNet-B0/B7 [75], CSPResNeXt50 [81], CSPDarknet53 [81] • Neck: • Additional blocks: SPP [25], ASPP [5], RFB [47], SAM [85] • Path-aggregation blocks: FPN [44], PAN [49], NAS-FPN [17], Fully-connected FPN, BiFPN [77], ASFF [48], SFAM [98] • Heads:: • Dense Prediction (one-stage): ◦ RPN [64], SSD [50], YOLO [61], RetinaNet ◦ CornerNet [37], CenterNet [13], MatrixNet [45] (anchor based) [60], FCOS [78] (anchor free) • Sparse Prediction (two-stage): ◦ Faster R-CNN [64], R-FCN [9], Mask R- ◦ RepPoints [87] (anchor free) CNN [23] (anchor based)

2.2. Bag of freebies Usually, a conventional object detector is trained off- line. Therefore, researchers always like to take this advan- tage and develop better training methods which can make the object detector receive better accuracy without increas- ing the inference cost. We call these methods that only change the training strategy or only increase the training cost as “bag of freebies.” What is often adopted by object detection methods and meets the deﬁnition of bag of free- bies is data augmentation. The purpose of data augmenta- tion is to increase the variability of the input images, so that the designed object detection model has higher robustness to the images obtained from different environments. For examples, photometric distortions and geometric distortions are two commonly used data augmentation method and they deﬁnitely beneﬁt the object detection task. In dealing with photometric distortion, we adjust the brightness, contrast, hue, saturation, and noise of an image. For geometric dis- tortion, we add random scaling, cropping, ﬂipping, and ro- tating. The data augmentation methods mentioned above are all pixel-wise adjustments, and all original pixel information in the adjusted area is retained. In addition, some researchers engaged in data augmentation put their emphasis on sim- ulating object occlusion issues. They have achieved good results in image classiﬁcation and object detection. For ex- ample, random erase [100] and CutOut [11] can randomly select the rectangle region in an image and ﬁll in a random or complementary value of zero. As for hide-and-seek [69] and grid mask [6], they randomly or evenly select multiple rectangle regions in an image and replace them to all ze- ros. If similar concepts are applied to feature maps, there are DropOut [71], DropConnect [80], and DropBlock [16] methods. In addition, some researchers have proposed the methods of using multiple images together to perform data augmentation. For example, MixUp [92] uses two images to multiply and superimpose with different coefﬁcient ra- tios, and then adjusts the label with these superimposed ra- tios. As for CutMix [91], it is to cover the cropped image to rectangle region of other images, and adjusts the label according to the size of the mix area. In addition to the above mentioned methods, style transfer GAN [15] is also used for data augmentation, and such usage can effectively reduce the texture bias learned by CNN. Different from the various approaches proposed above, some other bag of freebies methods are dedicated to solving the problem that the semantic distribution in the dataset may have bias. In dealing with the problem of semantic distri- bution bias, a very important issue is that there is a problem of data imbalance between different classes, and this prob- lem is often solved by hard negative example mining [72] or online hard example mining [67] in two-stage object de- tector. But the example mining method is not applicable 3 to one-stage object detector, because this kind of detector belongs to the dense prediction architecture. Therefore Lin et al. [45] proposed focal loss to deal with the problem of data imbalance existing between various classes. An- other very important issue is that it is difﬁcult to express the relationship of the degree of association between different categories with the one-hot hard representation. This rep- resentation scheme is often used when executing labeling. The label smoothing proposed in [73] is to convert hard la- bel into soft label for training, which can make model more robust. In order to obtain a better soft label, Islam et al. [33] introduced the concept of knowledge distillation to design the label reﬁnement network. The last bag of freebies is the objective function of Bounding Box (BBox) regression. The traditional object detector usually uses Mean Square Error (MSE) to di- rectly perform regression on the center point coordinates and height and width of the BBox, i.e., {xcenter, ycenter, w, h}, or the upper left point and the lower right point, i.e., {xtop lef t, ytop lef t, xbottom right, ybottom right}. As for anchor-based method, it is to estimate the correspond- for example {xcenter of f set, ycenter of f set, ing offset, wof f set, hof f set} and {xtop lef t of f set, ytop lef t of f set, xbottom right of f set, ybottom right of f set}. However, to di- rectly estimate the coordinate values of each point of the BBox is to treat these points as independent variables, but in fact does not consider the integrity of the object itself. In order to make this issue processed better, some researchers recently proposed IoU loss [90], which puts the coverage of predicted BBox area and ground truth BBox area into con- sideration. The IoU loss computing process will trigger the calculation of the four coordinate points of the BBox by ex- ecuting IoU with the ground truth, and then connecting the generated results into a whole code. Because IoU is a scale invariant representation, it can solve the problem that when traditional methods calculate the l1 or l2 loss of {x, y, w, h}, the loss will increase with the scale. Recently, some researchers have continued to improve IoU loss. For exam- ple, GIoU loss [65] is to include the shape and orientation of object in addition to the coverage area. They proposed to ﬁnd the smallest area BBox that can simultaneously cover the predicted BBox and ground truth BBox, and use this BBox as the denominator to replace the denominator origi- nally used in IoU loss. As for DIoU loss [99], it additionally considers the distance of the center of an object, and CIoU loss [99], on the other hand simultaneously considers the overlapping area, the distance between center points, and the aspect ratio. CIoU can achieve better convergence speed and accuracy on the BBox regression problem.

2.3. Bag of specials For those plugin modules and post-processing methods that only increase the inference cost by a small amount but can signiﬁcantly improve the accuracy of object detec- tion, we call them “bag of specials”. Generally speaking, these plugin modules are for enhancing certain attributes in a model, such as enlarging receptive ﬁeld, introducing at- tention mechanism, or strengthening feature integration ca- pability, etc., and post-processing is a method for screening model prediction results. Common modules that can be used to enhance recep- tive ﬁeld are SPP [25], ASPP [5], and RFB [47]. The SPP module was originated from Spatial Pyramid Match- ing (SPM) [39], and SPMs original method was to split fea- ture map into several d × d equal blocks, where d can be {1, 2, 3, ...}, thus forming spatial pyramid, and then extract- ing bag-of-word features. SPP integrates SPM into CNN and use max-pooling operation instead of bag-of-word op- eration. Since the SPP module proposed by He et al. [25] will output one dimensional feature vector, it is infeasible to be applied in Fully Convolutional Network (FCN). Thus in the design of YOLOv3 [63], Redmon and Farhadi improve SPP module to the concatenation of max-pooling outputs with kernel size k × k, where k = {1, 5, 9, 13}, and stride equals to 1. Under this design, a relatively large k × k max- pooling effectively increase the receptive ﬁeld of backbone feature. After adding the improved version of SPP module, YOLOv3-608 upgrades AP50 by 2.7% on the MS COCO object detection task at the cost of 0.5% extra computation. The difference in operation between ASPP [5] module and improved SPP module is mainly from the original k×k ker- nel size, max-pooling of stride equals to 1 to several 3 × 3 kernel size, dilated ratio equals to k, and stride equals to 1 in dilated convolution operation. RFB module is to use sev- eral dilated convolutions of k×k kernel, dilated ratio equals to k, and stride equals to 1 to obtain a more comprehensive spatial coverage than ASPP. RFB [47] only costs 7% extra inference time to increase the AP50 of SSD on MS COCO by 5.7%. The attention module that is often used in object detec- tion is mainly divided into channel-wise attention and point- wise attention, and the representatives of these two atten- tion models are Squeeze-and-Excitation (SE) [29] and Spa- tial Attention Module (SAM) [85], respectively. Although SE module can improve the power of ResNet50 in the Im- ageNet image classiﬁcation task 1% top-1 accuracy at the cost of only increasing the computational effort by 2%, but on a GPU usually it will increase the inference time by about 10%, so it is more appropriate to be used in mobile devices. But for SAM, it only needs to pay 0.1% extra cal- culation and it can improve ResNet50-SE 0.5% top-1 accu- racy on the ImageNet image classiﬁcation task. Best of all, it does not affect the speed of inference on the GPU at all. In terms of feature integration, the early practice is to use skip connection [51] or hyper-column [22] to integrate low- level physical feature to high-level semantic feature. Since multi-scale prediction methods such as FPN have become popular, many lightweight modules that integrate different feature pyramid have been proposed. The modules of this sort include SFAM [98], ASFF [48], and BiFPN [77]. The main idea of SFAM is to use SE module to execute channel- wise level re-weighting on multi-scale concatenated feature maps. As for ASFF, it uses softmax as point-wise level re- weighting and then adds feature maps of different scales. In BiFPN, the multi-input weighted residual connections is proposed to execute scale-wise level re-weighting, and then add feature maps of different scales. In the research of deep learning, some people put their focus on searching for good activation function. A good activation function can make the gradient more efﬁciently propagated, and at the same time it will not cause too much extra computational cost. In 2010, Nair and Hin- ton [56] propose ReLU to substantially solve the gradient vanish problem which is frequently encountered in tradi- tional tanh and sigmoid activation function. Subsequently, LReLU [54], PReLU [24], ReLU6 [28], Scaled Exponential Linear Unit (SELU) [35], Swish [59], hard-Swish [27], and Mish [55], etc., which are also used to solve the gradient vanish problem, have been proposed. The main purpose of LReLU and PReLU is to solve the problem that the gradi- ent of ReLU is zero when the output is less than zero. As for ReLU6 and hard-Swish, they are specially designed for quantization networks. For self-normalizing a neural net- work, the SELU activation function is proposed to satisfy the goal. One thing to be noted is that both Swish and Mish are continuously differentiable activation function. The post-processing method commonly used in deep- learning-based object detection is NMS, which can be used to ﬁlter those BBoxes that badly predict the same ob- ject, and only retain the candidate BBoxes with higher re- sponse. The way NMS tries to improve is consistent with the method of optimizing an objective function. The orig- inal method proposed by NMS does not consider the con- text information, so Girshick et al. [19] added classiﬁcation conﬁdence score in R-CNN as a reference, and according to the order of conﬁdence score, greedy NMS was performed in the order of high score to low score. As for soft NMS [1], it considers the problem that the occlusion of an object may cause the degradation of conﬁdence score in greedy NMS with IoU score. The DIoU NMS [99] developers way of thinking is to add the information of the center point dis- tance to the BBox screening process on the basis of soft NMS. It is worth mentioning that, since none of above post- processing methods directly refer to the captured image fea- tures, post-processing is no longer required in the subse- quent development of an anchor-free method. 4

Table 1: Parameters of neural networks for image classiﬁcation. Backbone model Input network resolution Receptive ﬁeld size Parameters CSPResNext50 CSPDarknet53 EfﬁcientNet-B3 (ours) 512x512 512x512 512x512 425x425 725x725 1311x1311 20.6 M 27.6 M 12.0 M Average size of layer output (WxHxC) 1058 K 950 K 668 K BFLOPs (512x512 network resolution) FPS (GPU RTX 2070) 31 (15.5 FMA) 52 (26.0 FMA) 11 (5.5 FMA) 62 66 26 3. Methodology The basic aim is fast operating speed of neural network, in production systems and optimization for parallel compu- tations, rather than the low computation volume theoreti- cal indicator (BFLOP). We present two options of real-time neural networks: • For GPU we use a small number of groups (1 - 8) in convolutional layers: CSPResNeXt50 / CSPDarknet53 • For VPU - we use grouped-convolution, but we re- frain from using Squeeze-and-excitement (SE) blocks - speciﬁcally this includes the following models: EfﬁcientNet-lite / MixNet [76] / GhostNet [21] / Mo- bileNetV3 3.1. Selection of architecture Our objective is to ﬁnd the optimal balance among the in- put network resolution, the convolutional layer number, the parameter number (ﬁlter size2 * ﬁlters * channel / groups), and the number of layer outputs (ﬁlters). For instance, our numerous studies demonstrate that the CSPResNext50 is considerably better compared to CSPDarknet53 in terms of object classiﬁcation on the ILSVRC2012 (ImageNet) dataset [10]. However, conversely, the CSPDarknet53 is better compared to CSPResNext50 in terms of detecting ob- jects on the MS COCO dataset [46]. The next objective is to select additional blocks for in- creasing the receptive ﬁeld and the best method of parame- ter aggregation from different backbone levels for different detector levels: e.g. FPN, PAN, ASFF, BiFPN. A reference model which is optimal for classiﬁcation is not always optimal for a detector. In contrast to the classi- ﬁer, the detector requires the following: • Higher input network size (resolution) – for detecting multiple small-sized objects • More layers – for a higher receptive ﬁeld to cover the increased size of input network • More parameters – for greater capacity of a model to detect multiple objects of different sizes in a single im- age Hypothetically speaking, we can assume that a model with a larger receptive ﬁeld size (with a larger number of convolutional layers 3 × 3) and a larger number of parame- ters should be selected as the backbone. Table 1 shows the information of CSPResNeXt50, CSPDarknet53, and Efﬁ- cientNet B3. The CSPResNext50 contains only 16 convo- lutional layers 3 × 3, a 425 × 425 receptive ﬁeld and 20.6 M parameters, while CSPDarknet53 contains 29 convolu- tional layers 3 × 3, a 725 × 725 receptive ﬁeld and 27.6 M parameters. This theoretical justiﬁcation, together with our numerous experiments, show that CSPDarknet53 neu- ral network is the optimal model of the two as the backbone for a detector. The inﬂuence of the receptive ﬁeld with different sizes is summarized as follows: • Up to the object size - allows viewing the entire object • Up to network size - allows viewing the context around the object • Exceeding the network size - increases the number of connections between the image point and the ﬁnal ac- tivation We add the SPP block over the CSPDarknet53, since it signiﬁcantly increases the receptive ﬁeld, separates out the most signiﬁcant context features and causes almost no re- duction of the network operation speed. We use PANet as the method of parameter aggregation from different back- bone levels for different detector levels, instead of the FPN used in YOLOv3. Finally, we choose CSPDarknet53 backbone, SPP addi- tional module, PANet path-aggregation neck, and YOLOv3 (anchor based) head as the architecture of YOLOv4. In the future we plan to expand signiﬁcantly the content of Bag of Freebies (BoF) for the detector, which theoreti- cally can address some problems and increase the detector accuracy, and sequentially check the inﬂuence of each fea- ture in an experimental fashion. We do not use Cross-GPU Batch Normalization (CGBN or SyncBN) or expensive specialized devices. This al- lows anyone to reproduce our state-of-the-art outcomes on a conventional graphic processor e.g. GTX 1080Ti or RTX 2080Ti. 5

3.2. Selection of BoF and BoS For improving the object detection training, a CNN usu- ally uses the following: • Activations: ReLU, leaky-ReLU, parametric-ReLU, ReLU6, SELU, Swish, or Mish • Bounding box regression loss: MSE, IoU, GIoU, CIoU, DIoU • Data augmentation: CutOut, MixUp, CutMix • Regularization method: DropOut, DropPath [36], Spatial DropOut [79], or DropBlock • Normalization of the network activations by their mean and variance: Batch Normalization (BN) [32], Cross-GPU Batch Normalization (CGBN or SyncBN) [93], Filter Response Normalization (FRN) [70], or Cross-Iteration Batch Normalization (CBN) [89] • Skip-connections: Residual connections, Weighted residual connections, Multi-input weighted residual connections, or Cross stage partial connections (CSP) As for training activation function, since PReLU and SELU are more difﬁcult to train, and ReLU6 is speciﬁcally designed for quantization network, we therefore remove the above activation functions from the candidate list. In the method of reqularization, the people who published Drop- Block have compared their method with other methods in detail, and their regularization method has won a lot. There- fore, we did not hesitate to choose DropBlock as our reg- ularization method. As for the selection of normalization method, since we focus on a training strategy that uses only one GPU, syncBN is not considered. 3.3. Additional improvements In order to make the designed detector more suitable for training on single GPU, we made additional design and im- provement as follows: • We introduce a new method of data augmentation Mo- saic, and Self-Adversarial Training (SAT) • We select optimal hyper-parameters while applying genetic algorithms • We modify some exsiting methods to make our design suitble for efﬁcient training and detection - modiﬁed SAM, modiﬁed PAN, and Cross mini-Batch Normal- ization (CmBN) Mosaic represents a new data augmentation method that mixes 4 training images. Thus 4 different contexts are Figure 3: Mosaic represents a new method of data augmen- tation. mixed, while CutMix mixes only 2 input images. This al- lows detection of objects outside their normal context. In addition, batch normalization calculates activation statistics from 4 different images on each layer. This signiﬁcantly reduces the need for a large mini-batch size. Self-Adversarial Training (SAT) also represents a new data augmentation technique that operates in 2 forward backward stages. In the 1st stage the neural network alters the original image instead of the network weights. In this way the neural network executes an adversarial attack on it- self, altering the original image to create the deception that there is no desired object on the image. In the 2nd stage, the neural network is trained to detect an object on this modiﬁed image in the normal way. Figure 4: Cross mini-Batch Normalization. CmBN represents a CBN modiﬁed version, as shown in Figure 4, deﬁned as Cross mini-Batch Normalization (CmBN). This collects statistics only between mini-batches within a single batch. We modify SAM from spatial-wise attention to point- wise attention, and replace shortcut connection of PAN to concatenation, as shown in Figure 5 and Figure 6, respec- tively. 6

4. Experiments We test the inﬂuence of different training improve- ment techniques on accuracy of the classiﬁer on ImageNet (ILSVRC 2012 val) dataset, and then on the accuracy of the detector on MS COCO (test-dev 2017) dataset. Figure 5: Modiﬁed SAM. Figure 6: Modiﬁed PAN. 3.4. YOLOv4 In this section, we shall elaborate the details of YOLOv4. YOLOv4 consists of: • Backbone: CSPDarknet53 [81] • Neck: SPP [25], PAN [49] • Head: YOLOv3 [63] YOLO v4 uses: • Bag of Freebies (BoF) for backbone: CutMix and Mosaic data augmentation, DropBlock regularization, Class label smoothing • Bag of Specials (BoS) for backbone: Mish activa- tion, Cross-stage partial connections (CSP), Multi- input weighted residual connections (MiWRC) • Bag of Freebies (BoF) for detector: CIoU-loss, CmBN, DropBlock regularization, Mosaic data aug- mentation, Self-Adversarial Training, Eliminate grid sensitivity, Using multiple anchors for a single ground truth, Cosine annealing scheduler [52], Optimal hyper- parameters, Random training shapes • Bag of Specials (BoS) for detector: Mish activation, SPP-block, SAM-block, PAN path-aggregation block, DIoU-NMS 7 4.1. Experimental setup In ImageNet image classiﬁcation experiments, the de- fault hyper-parameters are as follows: the training steps is 8,000,000; the batch size and the mini-batch size are 128 and 32, respectively; the polynomial decay learning rate scheduling strategy is adopted with initial learning rate 0.1; the warm-up steps is 1000; the momentum and weight de- cay are respectively set as 0.9 and 0.005. All of our BoS experiments use the same hyper-parameter as the default setting, and in the BoF experiments, we add an additional 50% training steps. In the BoF experiments, we verify MixUp, CutMix, Mosaic, Bluring data augmentation, and label smoothing regularization methods. In the BoS experi- ments, we compared the effects of LReLU, Swish, and Mish activation function. All experiments are trained with a 1080 Ti or 2080 Ti GPU. In MS COCO object detection experiments, the de- fault hyper-parameters are as follows: the training steps is 500,500; the step decay learning rate scheduling strategy is adopted with initial learning rate 0.01 and multiply with a factor 0.1 at the 400,000 steps and the 450,000 steps, re- spectively; The momentum and weight decay are respec- tively set as 0.9 and 0.0005. All architectures use a sin- gle GPU to execute multi-scale training in the batch size of 64 while mini-batch size is 8 or 4 depend on the ar- chitectures and GPU memory limitation. Except for us- ing genetic algorithm for hyper-parameter search experi- ments, all other experiments use default setting. Genetic algorithm used YOLOv3-SPP to train with GIoU loss and search 300 epochs for min-val 5k sets. We adopt searched learning rate 0.00261, momentum 0.949, IoU threshold for assigning ground truth 0.213, and loss normalizer 0.07 for genetic algorithm experiments. We have veriﬁed a large number of BoF, including grid sensitivity elimination, mo- saic data augmentation, IoU threshold, genetic algorithm, class label smoothing, cross mini-batch normalization, self- adversarial training, cosine annealing scheduler, dynamic mini-batch size, DropBlock, Optimized Anchors, different kind of IoU losses. We also conduct experiments on various BoS, including Mish, SPP, SAM, RFB, BiFPN, and Gaus- sian YOLO [8]. For all experiments, we only use one GPU for training, so techniques such as syncBN that optimizes multiple GPUs are not used.

4.2. Inﬂuence of different features on Classiﬁer training First, we study the inﬂuence of different features on classiﬁer training; speciﬁcally, the inﬂuence of Class la- bel smoothing, the inﬂuence of different data augmentation techniques, bilateral blurring, MixUp, CutMix and Mosaic, as shown in Fugure 7, and the inﬂuence of different activa- tions, such as Leaky-ReLU (by default), Swish, and Mish. Figure 7: Various method of data augmentation. In our experiments, as illustrated in Table 2, the clas- siﬁer’s accuracy is improved by introducing the features such as: CutMix and Mosaic data augmentation, Class la- bel smoothing, and Mish activation. As a result, our BoF- backbone (Bag of Freebies) for classiﬁer training includes the following: CutMix and Mosaic data augmentation and Class label smoothing. In addition we use Mish activation as a complementary option, as shown in Table 2 and Table 3. Table 2: Inﬂuence of BoF and Mish on the CSPResNeXt-50 clas- siﬁer accuracy. MixUp CutMix Mosaic Bluring Label Smoothing Swish Mish Top-1 Top-5 77.9% 94.0% 77.2% 94.0% 78.0% 94.3% 78.1% 94.5% 77.5% 93.8% 78.1% 94.4% 64.5% 86.0% 78.9% 94.5% 78.5% 94.8% 79.8% 95.2% Table 3: Inﬂuence of BoF and Mish on the CSPDarknet-53 classi- ﬁer accuracy. MixUp CutMix Mosaic Bluring Label Smoothing Swish Mish Top-1 Top-5 77.2% 93.6% 77.8% 94.4% 78.7% 94.8% 4.3. Inﬂuence of different features on Detector training Further study concerns the inﬂuence of different Bag-of- Freebies (BoF-detector) on the detector training accuracy, as shown in Table 4. We signiﬁcantly expand the BoF list through studying different features that increase the detector accuracy without affecting FPS: • S: Eliminate grid sensitivity the equation bx = σ(tx)+ cx, by = σ(ty) + cy, where cx and cy are always whole numbers, is used in YOLOv3 for evaluating the ob- ject coordinates, therefore, extremely high tx absolute values are required for the bx value approaching the cx or cx + 1 values. We solve this problem through multiplying the sigmoid by a factor exceeding 1.0, so eliminating the effect of grid on which the object is undetectable. • M: Mosaic data augmentation - using the 4-image mo- saic during training instead of single image • IT: IoU threshold - using multiple anchors for a single ground truth IoU (truth, anchor) > IoU threshold • GA: Genetic algorithms - using genetic algorithms for selecting the optimal hyperparameters during network training on the ﬁrst 10% of time periods • LS: Class label smoothing - using class label smooth- ing for sigmoid activation • CBN: CmBN - using Cross mini-Batch Normalization for collecting statistics inside the entire batch, instead of collecting statistics inside a single mini-batch • CA: Cosine annealing scheduler - altering the learning rate during sinusoid training • DM: Dynamic mini-batch size - automatic increase of mini-batch size during small resolution training by us- ing Random training shapes • OA: Optimized Anchors - using the optimized anchors for training with the 512x512 network resolution • GIoU, CIoU, DIoU, MSE - using different loss algo- rithms for bounded box regression Further study concerns the inﬂuence of different Bag- of-Specials (BoS-detector) on the detector training accu- racy, including PAN, RFB, SAM, Gaussian YOLO (G), and ASFF, as shown in Table 5. In our experiments, the detector gets best performance when using SPP, PAN, and SAM. 8

分享到：

赞收藏

资料库

YOLOv4论文.pdf

相关推荐

人工智能

热门标签

最新资料