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
Attention Decoupling for Query-Based Object Detection
TL;DR: This work introduces an attention decoupling (AD) for query-based detectors to explicitly align multi-task features and proposes a task consistency loss (TCL) which integrates a novel task alignment metric to classification loss to further improve task consistency across multiple decoding stages.
Aligning localization and classification for anchor-free object detection in aerial imagery
Cong Zhang,Yakun Ju,Jun Xiao,Yuting Yang,Kin-Man Lam +4 more
- 02 May 2024
TL;DR: Aligning localization and classification for anchor-free object detection in aerial imagery improves detection performance by explicitly pulling closer the predictions of localization and classification.
Vehicle Detection in UAV Remote Sensing Image Based on Improved YOLOv5
Lichuan Geng,Bangjin Wang +1 more
- 01 Nov 2022
TL;DR: In this article , the adaptive anchor frame calculation is used to seek the optimal initial value anchor frame, the loss function of YOLOv5 algorithm which only uses the length width ratio of the bounding box and cannot reflect the real difference between the width and height of the bounded box and its real value, is improved.
Microarmature Solder Surface Detection: An Adaptive Central Region Sample Selection Anchor Free Framework
TL;DR: In this paper , an adaptive label assignment detection framework is proposed for defect detection of microarmature solder surface defect detection, which uses an anchor free object detection network as the backbone and a feature compensation method is proposed to complement the spatial information for solving the feature disappearance problem of small objects.
Objects as Extreme Points
Yang Yang,Min Li,Bo Meng,Zihao Huang,Junxing Ren,Degang Sun +5 more
- 08 Nov 2021
TL;DR: Zhang et al. as discussed by the authors proposed an Extreme-Point-Prediction-Based object detector (EPP-Net), which directly regresses the relative displacement vector between each pixel and the four extreme points.
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.