paper-with-me

홈 › Papers

Rethinking Classification and Localization for Object Detection

2019-04-13 · CVPR 2020 6 · Yue Wu, Yinpeng Chen, Lu Yuan, Zicheng Liu, Lijuan Wang, Hongzhi Li, Yun Fu

Two head structures (i.e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks. However, there is a lack of understanding of how does these two head structures work for these two tasks. To address this issue, we perform a thorough analysis and find an interesting fact that the two head structures have opposite preferences towards the two tasks. Specifically, the fully connected head (fc-head) is more suitable for the classification task, while the convolution head (conv-head) is more suitable for the localization task. Furthermore, we examine the output feature maps of both heads and find that fc-head has more spatial sensitivity than conv-head. Thus, fc-head has more capability to distinguish a complete object from part of an object, but is not robust to regress the whole object. Based upon these findings, we propose a Double-Head method, which has a fully connected head focusing on classification and a convolution head for bounding box regression. Without bells and whistles, our method gains +3.5 and +2.8 AP on MS COCO dataset from Feature Pyramid Network (FPN) baselines with ResNet-50 and ResNet-101 backbones, respectively.

📄 PDF Abstract BibTeX arXiv:1904.06493

Code (2)

wuyuebupt/doubleheadsrcnn 공식 구현 pytorch
open-mmlab/mmdetection pytorch

Tasks

ClassificationGeneral ClassificationObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Average Pooling 설명 없음
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…
Mask R-CNN Mask R-CNN extends Faster R-CNN to solve instance segmentation tasks. It achieves this by adding a branch for predicting an…

Similar Papers 제목 키워드 기반

Rethinking Pseudo Labels for Semi-Supervised Object Detection

2021-06-01 · Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S. Davis

Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when usi…

Classificationimage-classificationImage ClassificationObject+3

Rethinking the Faster R-CNN Architecture for Temporal Action Localization

2018-04-20 · CVPR 2018 6 · Yu-Wei Chao, Sudheendra Vijayanarasimhan, Bryan Seybold, David A. Ross 외

We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key shortcomings of existing approaches: (1) we i…

Action ClassificationAction LocalizationGeneral Classificationobject-detection+2

Rethinking the Route Towards Weakly Supervised Object Localization

2020-02-26 · CVPR 2020 6 · Chen-Lin Zhang, Yun-Hao Cao, Jianxin Wu

Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels. Previous methods often try to utilize feature maps and classification weights to localize objects using image level anno…

General ClassificationObjectObject LocalizationWeakly-Supervised Object Localization

Rethinking Natural Adversarial Examples for Classification Models

2021-02-23 · Xiao Li, Jianmin Li, Ting Dai, Jie Shi 외

Recently, it was found that many real-world examples without intentional modifications can fool machine learning models, and such examples are called "natural adversarial examples". ImageNet-A is a famous dataset of natu…

ClassificationGeneral Classificationobject-detectionObject Detection

Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Driving

2026-07-02 · Adwait Chandorkar, Kai Krink, Yerdana Maulenbay, Hasan Tercan 외 arxiv

Recent advancements in LiDAR-only 3D object detection have demonstrated improved detection accuracy over benchmark datasets. However, the adversarial robustness of these models remains untested. Very few adversarial robu…

Adversarial Robustness3D Object DetectionAutonomous Driving