Proposal Feature Learning Using Proposal Relations for Weakly Supervised Object Detection
Lists
Only you see this
Abstract
Weakly Supervised Object Detection (WSOD) trains detectors using only image-level annotations. Most existing WSOD models are based on pre-computed proposals and do not fully explore the relations of proposals. In this work, we address this limitation by proposing two approaches of Proposal Feature Learning for WSOD (PFL-WSOD), which effectively capture intra-proposal relations and inter-proposal relations respectively, thus improving proposal representation. To extract intra-proposal relations, we propose to utilize Self-Attention on Single Proposal for capturing relations inside each proposal. For inter-proposal relations, we propose Salient Region Banks by capturing a unique type of inter-proposal relation called deep inclusion, which significantly improves proposal representation when used in synergy with contrastive learning. Experimental results on benchmarks demonstrate the effectiveness of our methods.
BibTeX
@inproceedings{wang2024proposal,
author = {Zhaofei Wang and Weijia Zhang and Min-Ling Zhang},
title = {{Proposal Feature Learning Using Proposal Relations for Weakly Supervised Object Detection}},
booktitle = {ICME},
year = {2024},
doi = {10.1109/icme57554.2024.10688185},
}Loading related content...