# TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs

arXiv: https://arxiv.org/abs/2111.13470 · HTML: https://mlsanity.com/paper/2111.13470/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 55 references that are in the map.
- First posted on arXiv 26 Nov 2021.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)
- [Stacked Attention Networks for Image Question Answering](https://mlsanity.com/paper/1511.02274/) (2015)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [FcaNet: Frequency Channel Attention Networks](https://mlsanity.com/paper/2012.11879/) (2020)
- [BAM: Bottleneck Attention Module](https://mlsanity.com/paper/1807.06514/) (2018)
- [Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2105.15075/) (2021)
- [Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks](https://mlsanity.com/paper/1810.12348/) (2018)
- [A2-Nets: Double Attention Networks](https://mlsanity.com/paper/1810.11579/) (2018)
- [Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks](https://mlsanity.com/paper/1808.08127/) (2018)

## Built on by (most cited first, 4 of 4)

- [Cross-Layer Retrospective Retrieving via Layer Attention](https://mlsanity.com/paper/2302.03985/) (2023)
- [A Generic Shared Attention Mechanism for Various Backbone Neural Networks](https://mlsanity.com/paper/2210.16101/) (2022)
- [CSA-Net: Channel-wise Spatially Autocorrelated Attention Networks](https://mlsanity.com/paper/2405.05755/) (2024)
- [BA-Net: Bridge Attention in Deep Neural Networks](https://mlsanity.com/paper/2410.07860/) (2024)

## Abstract (arXiv)

Attention modules for Convolutional Neural Networks (CNNs) are an effective method to enhance performance on multiple computer-vision tasks. While existing methods appropriately model channel-, spatial- and self-attention, they primarily operate in a feedforward bottom-up manner. Consequently, the attention mechanism strongly depends on the local information of a single input feature map and does not incorporate relatively semantically-richer contextual information available at higher layers that can specify "what and where to look" in lower-level feature maps through top-down information flow. Accordingly, in this work, we propose a lightweight top-down attention module (TDAM) that iteratively generates a "visual searchlight" to perform channel and spatial modulation of its inputs and outputs more contextually-relevant feature maps at each computation step. Our experiments indicate that TDAM enhances the performance of CNNs across multiple object-recognition benchmarks and outperforms prominent attention modules while being more parameter and memory efficient. Further, TDAM-based models learn to "shift attention" by localizing individual objects or features at each computation step without any explicit supervision resulting in a 5% improvement for ResNet50 on weakly-supervised object localization. Source code and models are publicly available at: https://github.com/shantanuj/TDAM_Top_down_attention_module .