Erasing Integrated Learning: A Simple Yet Effective Approach for Weakly Supervised Object Localization
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8763-8772
Abstract
Weakly supervised object localization (WSOL) aims to localize object with only weak supervision like image-level labels. However, a long-standing problem for available techniques based on the classification network is that they often result in highlighting the most discriminative parts rather than the entire extent of object. Nevertheless, trying to explore the integral extent of the object could degrade the performance of image classification on the contrary. To remedy this, we propose a simple yet powerful approach by introducing a novel adversarial erasing technique, erasing integrated learning (EIL). By integrating discriminative region mining and adversarial erasing in a single forward-backward propagation in a vanilla CNN, the proposed EIL explores the high response class-specific area and the less discriminative region simultaneously, thus could maintain high performance in classification and jointly discover the full extent of the object. Furthermore, we apply multiple EIL (MEIL) modules at different levels of the network in a sequential manner, which for the first time integrates semantic features of multiple levels and multiple scales through adversarial erasing learning. In particular, the proposed EIL and advanced MEIL both achieve a new state-of-the-art performance in CUB-200-2011 and ILSVRC 2016 benchmark, making significant improvement in localization while advancing high performance in image classification.Keywords
This publication has 37 references indexed in Scilit:
- A Dual-Network Progressive Approach to Weakly Supervised Object Detection2017
- A brief introduction to weakly supervised learningNational Science Review, 2017
- Feature Pyramid Networks for Object Detection2017
- Weakly Supervised Cascaded Convolutional Networks2017
- Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach2017
- Selective Convolutional Descriptor Aggregation for Fine-Grained Image RetrievalIEEE Transactions on Image Processing, 2017
- Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation2016
- Rethinking the Inception Architecture for Computer Vision2016
- Learning Deep Features for Discriminative Localization2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015