Proposal Learning for Semi-Supervised Object Detection

01/15/2020
by   Peng Tang, et al.
11

In this paper, we focus on semi-supervised object detection to boost accuracies of proposal-based object detectors (a.k.a. two-stage object detectors) by training on both labeled and unlabeled data. However, it is non-trivial to train object detectors on unlabeled data due to the unavailability of ground truth labels. To address this problem, we present a proposal learning approach to learn proposal features and predictions from both labeled and unlabeled data. The approach consists of a self-supervised proposal learning module and a consistency-based proposal learning module. In the self-supervised proposal learning module, we present a proposal location loss and a contrastive loss to learn context-aware and noise-robust proposal features respectively. In the consistency-based proposal learning module, we apply consistency losses to both bounding box classification and regression predictions of proposals to learn noise-robust proposal features and predictions. Experiments are conducted on the COCO dataset with all available labeled and unlabeled data. Results show that our approach consistently improves the accuracies of fully-supervised baselines. In particular, after combining with data distillation, our approach improves AP by about 2.0 0.9 baselines respectively.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/07/2021

Self-Supervised Learning for Semi-Supervised Temporal Action Proposal

Self-supervised learning presents a remarkable performance to utilize un...
research
05/21/2022

ADT-SSL: Adaptive Dual-Threshold for Semi-Supervised Learning

Semi-Supervised Learning (SSL) has advanced classification tasks by inpu...
research
12/12/2017

Data Distillation: Towards Omni-Supervised Learning

We investigate omni-supervised learning, a special regime of semi-superv...
research
04/26/2022

Leveraging Unlabeled Data for Sketch-based Understanding

Sketch-based understanding is a critical component of human cognitive le...
research
08/29/2022

Open-Set Semi-Supervised Object Detection

Recent developments for Semi-Supervised Object Detection (SSOD) have sho...
research
10/16/2022

Towards Effective Image Manipulation Detection with Proposal Contrastive Learning

Deep models have been widely and successfully used in image manipulation...
research
07/29/2016

A Non-Parametric Learning Approach to Identify Online Human Trafficking

Human trafficking is among the most challenging law enforcement problems...

Please sign up or login with your details

Forgot password? Click here to reset