Recurrent Soft Attention Model for Common Object Recognition

2017/05/04 by Liliang Ren, Ren, Liliang
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #Visual Attention and Saliency Detection #cs.CV

paper · pdf · doi:10.48550/arxiv.1705.01921

5 pages, 4 figures

arxiv created 2017/05/29 · arxiv updated 2017/05/30

Abstract

We propose the Recurrent Soft Attention Model, which integrates the visual attention from the original image to a LSTM memory cell through a down-sample network. The model recurrently transmits visual attention to the memory cells for glimpse mask generation, which is a more natural way for attention integration and exploitation in general object detection and recognition problem. We test our model under the metric of the top-1 accuracy on the CIFAR-10 dataset. The experiment shows that our down-sample network and feedback mechanism plays an effective role among the whole network structure.

Related

• Where to Look: A Unified Attention Model for Visual Recognition with Reinforcement Learning
• Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition
• RATM: Recurrent Attentive Tracking Model
• DIANet: Dense-and-Implicit Attention Network
• CRAM: Clued Recurrent Attention Model