Rethinking Classification and Localization for Object Detection
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.
Code (2)
Tasks
ClassificationGeneral ClassificationObjectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Rethinking Pseudo Labels for Semi-Supervised Object Detection
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+3Rethinking the Faster R-CNN Architecture for Temporal Action Localization
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+2Rethinking the Route Towards Weakly Supervised Object Localization
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 LocalizationRethinking Natural Adversarial Examples for Classification Models
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 DetectionComprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Driving
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