Paper Info
Title
End-to-End Weakly Supervised Object Detection with Sparse Proposal Evolution.
Abstract
Conventional methods for weakly supervised object detection (WSOD) typically enumerate dense proposals and select the discriminative proposals as objects. However, these two-stage “enumerate-and-select” methods suffer object feature ambiguity brought by dense proposals and low detection efficiency caused by the proposal enumeration procedure. In this study, we propose a sparse proposal evolution (SPE) approach, which advances WSOD from the two-stage pipeline with dense proposals to an end-to-end framework with sparse proposals. SPE is built upon a visual transformer equipped with a seed proposal generation (SPG) branch and a sparse proposal refinement (SPR) branch. SPG generates high-quality seed proposals by taking advantage of the cascaded self-attention mechanism of the visual transformer, and SPR trains the detector to predict sparse proposals which are supervised by the seed proposals in a one-to-one matching fashion. SPG and SPR are iteratively performed so that seed proposals update to accurate supervision signals and sparse proposals evolve to precise object regions. Experiments on VOC and COCO object detection datasets show that SPE outperforms the state-of-the-art end-to-end methods by 7.0% mAP and 8.1% AP50. It is an order of magnitude faster than the two-stage methods, setting the first solid baseline for end-to-end WSOD with sparse proposals. The code is available at https://github.com/MingXiangL/SPE.
Year
DOI
Venue
2022
10.1007/978-3-031-20077-9_13
European Conference on Computer Vision
Keywords
DocType
Citations 
Weakly supervised object detection,Sparse proposals,Proposal evolution,End-to-end training
Conference
0
PageRank 
References 
Authors
0.34
0
9
Name
Order
Citations
PageRank
Mingxiang Liao100.34
Fang Wan2213.44
Yuan Yao380.93
Zhenjun Han417616.40
Zou Jialing500.34
Yuze Wang600.34
Bailan Feng700.68
Peng Yuan800.68
Qixiang Ye901.35