YOLO V1

本文由用户“samsonjie”分享发布更新时间：2020-03-20 13:27:28 举报文档

以下为《YOLO V1》的无排版文字预览，完整格式请下载

下载前请仔细阅读文字预览以及下方图片预览。图片预览是什么样的，下载的文档就是什么样的。

You Only Look Once: Uni?ed, Real-Time Object Detection Joseph Redmon∗, Santosh Divvala∗†, Ross Girshick¶, Ali Farhadi∗† University of Washington∗, Allen Institute for AI†, Facebook AI Research¶ http://pjreddie.com/yolo/ arXiv:1506.02640v5 [cs.CV] 9 May 2016 Abstract We present YOLO, a new approach to object detection. Prior work on object detection repurposes classi?ers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our uni?ed architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork. 1. Introduction Humans glance at an image and instantly know what objects are in the image, where they are, and how they interact. The human visual system is fast and accurate, allowing us to perform complex tasks like driving with little conscious thought. Fast, accurate algorithms for object detection would allow computers to drive cars without specialized sensors, enable assistive devices to convey real-time scene information to human users, and unlock the potential for general purpose, responsive robotic systems. Current detection systems repurpose classi?ers to perform detection. To detect an object, these systems take a classi?er for that object and evaluate it at various locations and scales in a test image. Systems like deformable parts models (DPM) use a sliding window approach where the classi?er is run at evenly spaced locations over the entire image [10]. More recent approaches like R-CNN use region proposal 1. Resize image. 2. Run convolutional network. 3. Non-max suppression. Person: 0.64 Dog: 0.30 Horse: 0.28 Figure 1: The YOLO Detection System. Processing images with YOLO is simple and straightforward. Our system (1) resizes the input image to 448 × 448, (2) runs a single convolutional network on the image, and (3) thresholds the resulting detections by the model’s con?dence. methods to ?rst generate potential bounding boxes in an image and then run a classi?er on these proposed boxes. After classi?cation, post-processing is used to re?ne the bounding boxes, eliminate duplicate detections, and rescore the boxes based on other objects in the scene [13]. These complex pipelines are slow and hard to optimize because each individual component must be trained separately. We reframe object detection as a single regression problem, straight from image pixels to bounding box coordinates and class probabilities. Using our system, you only look once (YOLO) at an image to predict what objects are present and where they are. YOLO is refreshingly simple: see Figure 1. A single convolutional network simultaneously predicts multiple bounding boxes and class probabilities for those boxes. YOLO trains on full images and directly optimizes detection performance. This uni?ed model has several bene?ts over traditional methods of object detection. First, YOLO is extremely fast. Since we frame detection as a regression problem we don’t need a complex pipeline. We simply run our neural network on a new image at test time to predict detections. Our base network runs at 45 frames per second with no batch processing on a Titan X GPU and a fast version runs at more than 150 fps. This means we can process streaming video in real-time with less than 25 milliseconds of latency. Furthermore, YOLO achieves more than twice the mean average precision of other real-time systems. For a demo of our system running in real-time on a webcam please see our project webpage: http://pjreddie.com/yolo/. Second, YOLO reasons globally about the image when 1 making predictions. Unlike sliding window and region proposal-based techniques, YOLO sees the entire image during training and test time so it implicitly encodes contextual information about classes as well as their appearance. Fast R-CNN, a top detection method [14], mistakes background patches in an image for objects because it can’t see the larger context. YOLO makes less than half the number of background errors compared to Fast R-CNN. Third, YOLO learns generalizable representations of objects. When trained on natural images and tested on artwork, YOLO outperforms top detection methods like DPM and R-CNN by a wide margin. Since YOLO is highly generalizable it is less likely to break down when applied to new domains or unexpected inputs. YOLO still lags behind state-of-the-art detection systems in accuracy. While it can quickly identify objects in images it struggles to precisely localize some objects, especially small ones. We examine these tradeoffs further in our experiments. All of our training and testing code is open source. A variety of pretrained models are also available to download. 2. Uni?ed Detection We unify the separate components of object detection into a single neural network. Our network uses features from the entire image to predict each bounding box. It also predicts all bounding boxes across all classes for an image simultaneously. This means our network reasons globally about the full image and all the objects in the image. The YOLO design enables end-to-end training and realtime speeds while maintaining high average precision. Our system divides the input image into an S × S grid. If the center of an object falls into a grid cell, that grid cell is responsible for detecting that object. Each grid cell predicts B bounding boxes and con?dence scores for those boxes. These con?dence scores re?ect how con?dent the model is that the box contains an object and also how accurate it thinks the box is that it predicts. Formally we de?ne con?dence as Pr(Object) ∗ IOUtprruetdh. If no object exists in that cell, the con?dence scores should be zero. Otherwise we want the con?dence score to equal the intersection over union (IOU) between the predicted box and the ground truth. Each bounding box consists of 5 predictions: x, y, w, h, and con?dence. The (x, y) coordinates represent the center of the box relative to the bounds of the grid cell. The width and height are predicted relative to the whole image. Finally the con?dence prediction represents the IOU between the predicted box and any ground truth box. Each grid cell also predicts C conditional class probabilities, Pr(Classi|Object). These probabilities are conditioned on the grid cell containing an object. We only predict one set of class probabilities per grid cell, regardless of the number of boxes B. At test time we multiply the conditional class probabilities and the individual box con?dence predictions, Pr(Classi|Object) ∗ Pr(Object) ∗ IOUtprruetdh = Pr(Classi) ∗ IOUtprruetdh (1) which gives us class-speci?c con?dence scores for each box. These scores encode both the probability of that class appearing in the box and how well the predicted box ?ts the object. Bounding boxes + confidence S × S grid on input Final detections Class probability map Figure 2: The Model. Our system models detection as a regression problem. It divides the image into an S × S grid and for each grid cell predicts B bounding boxes, con?dence for those boxes, and C class probabilities. These predictions are encoded as an S × S × (B ∗ 5 + C) tensor. For evaluating YOLO on PASCAL VOC, we use S = 7, B = 2. PASC 内容过长，仅展示头部和尾部部分文字预览，全文请查看图片预览。 47, 2001. 4 [37] P. Viola and M. J. Jones. Robust real-time face detection. International journal of computer vision, 57(2):137–154, 2004. 5 [38] J. Yan, Z. Lei, L. Wen, and S. Z. Li. The fastest deformable part model for object detection. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on, pages 2497–2504. IEEE, 2014. 5, 6 [39] C. L. Zitnick and P. Dolla´r. Edge boxes: Locating object proposals from edges. In Computer Vision–ECCV 2014, pages 391–405. Springer, 2014. 4 [文章尾部最后500字内容到此结束,中间部分内容请查看底下的图片预览]请点击下方选择您需要的文档下载。

以上为《YOLO V1》的无排版文字预览，完整格式请下载

下载前请仔细阅读上面文字预览以及下方图片预览。图片预览是什么样的，下载的文档就是什么样的。

YOLO V1

图片预览

热门关注

相关下载