Rethinking Pseudo Labels for Semi-Supervised Object Detection

06/01/2021
by   Hengduo Li, et al.
0

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 using pseudo labels, there is a lack of consideration in localization precision and amplified class imbalance, both of which are critical for detection tasks. In this paper, we introduce certainty-aware pseudo labels tailored for object detection, which can effectively estimate the classification and localization quality of derived pseudo labels. This is achieved by converting conventional localization as a classification task followed by refinement. Conditioned on classification and localization quality scores, we dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem. Extensive experiments demonstrate that our method improves state-of-the-art SSOD performance by 1-2 and 4-6 regime, our approach improves supervised baselines by up to 10 1-10

READ FULL TEXT

page 3

page 8

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
03/23/2022

Scale-Equivalent Distillation for Semi-Supervised Object Detection

Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based...
research
07/07/2022

Semi-supervised Object Detection via Virtual Category Learning

Due to the costliness of labelled data in real-world applications, semi-...
research
04/09/2022

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

Single-stage detectors suffer from extreme foreground-background class i...
research
03/27/2023

Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection

With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage...
research
02/15/2023

Semi-Supervised Deep Regression with Uncertainty Consistency and Variational Model Ensembling via Bayesian Neural Networks

Deep regression is an important problem with numerous applications. Thes...
research
04/16/2020

Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection

Important people detection is to automatically detect the individuals wh...

Please sign up or login with your details

Forgot password? Click here to reset