Attention-based Dropout Layer for Weakly Supervised Object Localization

Abstract

Weakly Supervised Object Localization (WSOL) techniques learn the object location only using image-level labels, without location annotations. A common limitation for these techniques is that they cover only the most discriminative part of the object, not the entire object. To address this problem, we propose an Attention-based Dropout Layer (ADL), which utilizes the self-attention mechanism to process the feature maps of the model. The proposed method is composed of two key components: 1) hiding the most discriminative part from the model for capturing the integral extent of object, and 2) highlighting the informative region for improving the recognition power of the model. Based on extensive experiments, we demonstrate that the proposed method is effective to improve the accuracy of WSOL, achieving a new state-of-the-art localization accuracy in CUB-200-2011 dataset. We also show that the proposed method is much more efficient in terms of both parameter and computation overheads than existing techniques.

CVPR 2019 (Oral)

References in corpus (8)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• Image Transformer
• Few-Example Object Detection with Model Communication
• Weakly-supervised Discovery of Visual Pattern Configurations
• On learning to localize objects with minimal supervision
• Soft Proposal Networks for Weakly Supervised Object Localization

Cited by in corpus (7)

• Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
• Shallow Feature Matters for Weakly Supervised Object Localization
• On the Benefits of Models with Perceptually-Aligned Gradients
• MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization
• Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification
• Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection
• Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation