Progressive Attention Networks for Visual Attribute Prediction

Abstract

We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process over multiple layers of a convolutional neural network. The attentive process in each layer determines whether to pass or block features at certain spatial locations for use in the subsequent layers. The proposed progressive attention mechanism works well especially when combined with hard attention. We further employ local contexts to incorporate neighborhood features of each location and estimate a better attention probability map. The experiments on synthetic and real datasets show that the proposed attention networks outperform traditional attention methods in visual attribute prediction tasks.

BMVC 2018 accepted paper

Cited by in corpus (8)

• Visual Reference Resolution using Attention Memory for Visual Dialog
• SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
• PA-GAN: Progressive Attention Generative Adversarial Network for Facial Attribute Editing
• Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustness
• Epipolar-Guided Deep Object Matching for Scene Change Detection
• FPAN: Fine-grained and Progressive Attention Localization Network for Data Retrieval
• Attentional Bottleneck: Towards an Interpretable Deep Driving Network
• Attention-Mechanism-based Tracking Method for Intelligent Internet of Vehicles