Rethinking the Route Towards Weakly Supervised Object Localization

CVPR 2020  ·  Chen-Lin Zhang, Yun-Hao Cao, Jianxin Wu ·

Weakly supervised object localization (WSOL) aims to localize objects with only image-level labels. Previous methods often try to utilize feature maps and classification weights to localize objects using image level annotations indirectly. In this paper, we demonstrate that weakly supervised object localization should be divided into two parts: class-agnostic object localization and object classification. For class-agnostic object localization, we should use class-agnostic methods to generate noisy pseudo annotations and then perform bounding box regression on them without class labels. We propose the pseudo supervised object localization (PSOL) method as a new way to solve WSOL. Our PSOL models have good transferability across different datasets without fine-tuning. With generated pseudo bounding boxes, we achieve 58.00% localization accuracy on ImageNet and 74.97% localization accuracy on CUB-200, which have a large edge over previous models.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Results from the Paper


Ranked #2 on Weakly-Supervised Object Localization on CUB-200-2011 (Top-1 Localization Accuracy metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Weakly-Supervised Object Localization CUB-200-2011 PSOL-DenseNet161-Sep Top-1 Localization Accuracy 74.97 # 2

Methods


No methods listed for this paper. Add relevant methods here