Attention Mechanisms

Recurrent models of visual attention

Introduced by Mnih et al. in Recurrent Models of Visual Attention

RAM adopts RNNs and reinforcement learning (RL) to make the network learn where to pay attention.

Source: Recurrent Models of Visual Attention


Paper Code Results Date Stars


Task Papers Share
Image Classification 10 8.40%
Quantization 6 5.04%
Semantic Segmentation 6 5.04%
Edge-computing 5 4.20%
Retrieval 3 2.52%
Federated Learning 3 2.52%
Image Segmentation 2 1.68%
Object Detection 2 1.68%
Anomaly Detection 2 1.68%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign