Recurrent Soft Attention Model for Common Object Recognition

by   Liliang Ren, et al.
Shanghai Jiao Tong University

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.


Reconstruction-guided attention improves the robustness and shape processing of neural networks

Many visual phenomena suggest that humans use top-down generative or rec...

Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition

The visual system processes a scene using a sequence of selective glimps...

Conditionally Learn to Pay Attention for Sequential Visual Task

Sequential visual task usually requires to pay attention to its current ...

Enriched Deep Recurrent Visual Attention Model for Multiple Object Recognition

We design an Enriched Deep Recurrent Visual Attention Model (EDRAM) - an...

Teaching Machines to Code: Neural Markup Generation with Visual Attention

We present a deep recurrent neural network model with soft visual attent...

CHAM: action recognition using convolutional hierarchical attention model

Recently, the soft attention mechanism, which was originally proposed in...

CRAM: Clued Recurrent Attention Model

To overcome the poor scalability of convolutional neural network, recurr...

Please sign up or login with your details

Forgot password? Click here to reset