Open AccessPosted Content
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
1K
TL;DR: An Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them.
read more
Abstract: Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point. This shows that how to select positive and negative training samples is important for current object detectors. Then, we propose an Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object. It significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them. Finally, we discuss the necessity of tiling multiple anchors per location on the image to detect objects. Extensive experiments conducted on MS COCO support our aforementioned analysis and conclusions. With the newly introduced ATSS, we improve state-of-the-art detectors by a large margin to $50.7\%$ AP without introducing any overhead. The code is available at this https URL
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Data Enhancement for Deep Learning-Based Wrist Fracture Detection
Weijie Huang,Fuqiang Sun,Menghua Zhang,Yongfeng Zhang,Changhui Ma +4 more
- 23 Aug 2021
TL;DR: Wang et al. as discussed by the authors proposed a data enhancement method based on image mosaic, which is embedded into several existing deep learning frameworks for verification, and the experimental results show that the proposed data enhancing method is universal to the existing DNN frameworks, and their AP value will be improved by 3%.
1
Object Occlusion of Adding New Categories in Objection Detection
Boyang Deng,M Lin,Shoulun Long +2 more
TL;DR: This work performs a systematic study of the Object Occlusion data collection and augmentation methods where it is shown that the simple mechanism of object occlusion is good enough and can provide acceptable accuracy in real scenarios adding new category.
Surgical action detection based on path aggregation adaptive spatial network
TL;DR: A path aggregation adaptive spatial feature pyramid network (PAAS-FPN), which combines bottom-up path enhancement and an adaptive spatial fusion mechanism, which achieves the highest detection accuracy in several experiments, thereby confirming its effectiveness in surgeon action detection.
1
Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization
Edward Fish,Jon Weinbren,Andrew Gilbert +2 more
TL;DR: The Multi-Resolution Audio-Visual Feature Fusion (MRAV-FF) is introduced, an innovative method to merge audio-visual data across different temporal resolutions and is compatible with existing FPN TAL architectures and offering a significant enhancement in performance when audio data is available.
DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification
Shuguang Dou,Xiangyang Jiang,Yuanpeng Tu,Junyao Gao,Zefan Qu,Qingsong Zhao,Cairong Zhao +6 more
TL;DR: The paper introduces the Decouple Re-identificatiOn and human Parsing (DROP) method for occluded person re-identification (ReID), arguing that the inferior performance of the former is due to distinct granularity requirements for ReID and human parsing features.
1
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
- 06 Sep 2014
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon,Santosh K. Divvala,Ross Girshick,Ali Farhadi +3 more
- 27 Jun 2016
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.