Proceedings Article10.1109/CVPR52688.2022.00958
Semi-Supervised Object Detection via Multi-instance Alignment with Global Class Prototypes
Aoxue Li,Peng Yuan,Zhenguo Li +2 more
- 01 Jun 2022
pp 9799-9808
8
TL;DR: A Multi-instance Alignment model which enhances the prediction consistency based on Global Class Proto-types (MA-GCP) and imposes the consistency between pseudo ground-truths and their high-IoU candi-dates by minimizing the cross-entropy loss of their class distributions computed based on global class prototypes.
read more
Abstract: Semi-Supervised object detection (SSOD) aims to improve the generalization ability of object detectors with large-scale unlabeled images. Current pseudo-labeling-based SSOD methods individually learn from labeled data and unlabeled data, without considering the relation be-tween them. To make full use of labeled data, we pro-pose a Multi-instance Alignment model which enhances the prediction consistency based on Global Class Proto-types (MA-GCP). Specifically, we impose the consistency between pseudo ground-truths and their high-IoU candi-dates by minimizing the cross-entropy loss of their class distributions computed based on global class prototypes. These global class prototypes are estimated with the whole labeled dataset via the exponential moving average algorithm. To evaluate the proposed MA-GCP model, we inte-grate it into the state-of-the-art SSOD framework and ex-periments on two benchmark datasets demonstrate the ef-fectiveness of our MA-GCP approach.
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
Adapting Object Size Variance and Class Imbalance for Semi-supervised Object Detection
TL;DR: Zhang et al. as discussed by the authors proposed an adaptive pseudo labeling strategy, which can assign thresholds to classes with respect to their "hardness" to ensure the high quality of easier classes and increasing the quantity of harder classes simultaneously.
De-biased Teacher: Rethinking IoU Matching for Semi-supervised Object Detection
TL;DR: De-biased teacher as mentioned in this paper is a semi-supervised object detection method that abandons both the IoU matching and pseudo labeling processes by directly generating favorable training proposals for consistency regularization between the weak/strong augmented image pairs.
Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty
H. Choi,Zhixiang Chen,Xuepeng Shi,Tae-Kyun Kim +3 more
- 06 Dec 2022
TL;DR: Zhang et al. as mentioned in this paper proposed a two-step pseudo-label filtering for the classification and regression heads in a teacher-student framework, in which a teacher network generates pseudo-labels for unlabeled data to assist the training of a student network.
Pseudo-label Correction and Learning For Semi-Supervised Object Detection
TL;DR: In this paper , a multi-round refining and multi-vote weighting method was proposed to improve the stability of pseudo-labels and improve the performance of semi-supervised object detection.
2
Dual-Curriculum Teacher for Domain-Inconsistent Object Detection in Autonomous Driving
Long Long Yu,Yifan Zhang,Lanqing Hong,Fei Chen,Zhenguo Li +4 more
- 17 Oct 2022
TL;DR: A novel method, namely Dual-Curriculum Teacher (DucTeacher), which can calibrate biased pseudo-labels and handle the domain-inconsistent SSOD problem effectively and shows its advantages on SODA10M, the largest public semi-supervised autonomous driving dataset, and COCO, a widely used SSOD benchmark.
References
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.
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin,Piotr Dollár,Ross Girshick,Kaiming He,Bharath Hariharan,Serge Belongie +5 more
- 21 Jul 2017
TL;DR: This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
The Pascal Visual Object Classes (VOC) Challenge
TL;DR: The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse.
•Posted Content
A Simple Framework for Contrastive Learning of Visual Representations
TL;DR: It is shown that composition of data augmentations plays a critical role in defining effective predictive tasks, and introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning.