Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection

03/27/2023
by   Chang Liu, et al.
0

With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection ambiguity that selected pseudo labels are less accurate, since classification scores cannot properly represent the localization quality. (2) Assignment ambiguity that samples are matched with improper labels in pseudo-label assignment, as the strategy is misguided by missed objects and inaccurate pseudo boxes. To tackle these problems, we propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Specifically, to alleviate the selection ambiguity, Joint-Confidence Estimation (JCE) is proposed to jointly quantifies the classification and localization quality of pseudo labels. As for the assignment ambiguity, Task-Separation Assignment (TSA) is introduced to assign labels based on pixel-level predictions rather than unreliable pseudo boxes. It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity. Comprehensive experiments demonstrate that ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC. Codes can be found at https://github.com/PaddlePaddle/PaddleDetection.

READ FULL TEXT
research
07/16/2023

Semi-DETR: Semi-Supervised Object Detection with Detection Transformers

We analyze the DETR-based framework on semi-supervised object detection ...
research
04/09/2022

S4OD: Semi-Supervised learning for Single-Stage Object Detection

Single-stage detectors suffer from extreme foreground-background class i...
research
03/06/2023

Pseudo-label Correction and Learning For Semi-Supervised Object Detection

Pseudo-Labeling has emerged as a simple yet effective technique for semi...
research
06/01/2021

Rethinking Pseudo Labels for Semi-Supervised Object Detection

Recent advances in semi-supervised object detection (SSOD) are largely d...
research
04/15/2022

Dense Learning based Semi-Supervised Object Detection

Semi-supervised object detection (SSOD) aims to facilitate the training ...
research
07/06/2022

Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection

To date, the most powerful semi-supervised object detectors (SS-OD) are ...
research
12/16/2021

Classification Under Ambiguity: When Is Average-K Better Than Top-K?

When many labels are possible, choosing a single one can lead to low pre...

Please sign up or login with your details

Forgot password? Click here to reset