# Dynamic Region-Aware Convolution

arXiv: https://arxiv.org/abs/2003.12243 · HTML: https://mlsanity.com/paper/2003.12243/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2020.

## Built on by (most cited first, 30 of 50)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Delivering Arbitrary-Modal Semantic Segmentation](https://mlsanity.com/paper/2303.01480/) (2023)
- [Contextual Transformer Networks for Visual Recognition](https://mlsanity.com/paper/2107.12292/) (2021)
- [Image Synthesis via Semantic Composition](https://mlsanity.com/paper/2109.07053/) (2021)
- [MixFormer: Mixing Features across Windows and Dimensions](https://mlsanity.com/paper/2204.02557/) (2022)
- [StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation](https://mlsanity.com/paper/2408.01343/) (2024)
- [AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition](https://mlsanity.com/paper/2112.14238/) (2021)
- [HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks](https://mlsanity.com/paper/2305.06382/) (2023)
- [TAda! Temporally-Adaptive Convolutions for Video Understanding](https://mlsanity.com/paper/2110.06178/) (2021)
- [Revisiting Dynamic Convolution via Matrix Decomposition](https://mlsanity.com/paper/2103.08756/) (2021)
- [Pinwheel-shaped Convolution and Scale-based Dynamic Loss for Infrared Small Target Detection](https://mlsanity.com/paper/2412.16986/) (2024)
- [GaitGCI: Generative Counterfactual Intervention for Gait Recognition](https://mlsanity.com/paper/2306.03428/) (2023)
- [MicroNet: Improving Image Recognition with Extremely Low FLOPs](https://mlsanity.com/paper/2108.05894/) (2021)
- [Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentation](https://mlsanity.com/paper/2407.11344/) (2024)
- [Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening](https://mlsanity.com/paper/2404.07543/) (2024)
- [ELSA: Enhanced Local Self-Attention for Vision Transformer](https://mlsanity.com/paper/2112.12786/) (2021)
- [RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization](https://mlsanity.com/paper/2211.06088/) (2022)
- [U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation](https://mlsanity.com/paper/2405.15365/) (2024)
- [NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition](https://mlsanity.com/paper/2111.12994/) (2021)
- [Hierarchical Dynamic Image Harmonization](https://mlsanity.com/paper/2211.08639/) (2022)
- [Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal](https://mlsanity.com/paper/2306.09008/) (2023)
- [MMSFormer: Multimodal Transformer for Material and Semantic Segmentation](https://mlsanity.com/paper/2309.04001/) (2023)
- [Decomposed Guided Dynamic Filters for Efficient RGB-Guided Depth Completion](https://mlsanity.com/paper/2309.02043/) (2023)
- [Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition](https://mlsanity.com/paper/2412.11228/) (2024)
- [Orientation and Context Entangled Network for Retinal Vessel Segmentation](https://mlsanity.com/paper/2207.11396/) (2022)
- [AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutions](https://mlsanity.com/paper/2305.03387/) (2023)
- [Region-Adaptive Transform with Segmentation Prior for Image Compression](https://mlsanity.com/paper/2403.00628/) (2024)
- [TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing](https://mlsanity.com/paper/2203.10489/) (2022)
- [Temporally-Adaptive Models for Efficient Video Understanding](https://mlsanity.com/paper/2308.05787/) (2023)
- [ShareCMP: Polarization-Aware RGB-P Semantic Segmentation](https://mlsanity.com/paper/2312.03430/) (2023)

## Abstract (arXiv)

We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms standard convolution in modeling semantic variations. Standard convolutional layer can increase the number of filers to extract more visual elements but results in high computational cost. More gracefully, our DRConv transfers the increasing channel-wise filters to spatial dimension with learnable instructor, which not only improve representation ability of convolution, but also maintains computational cost and the translation-invariance as standard convolution dose. DRConv is an effective and elegant method for handling complex and variable spatial information distribution. It can substitute standard convolution in any existing networks for its plug-and-play property, especially to power convolution layers in efficient networks. We evaluate DRConv on a wide range of models (MobileNet series, ShuffleNetV2, etc.) and tasks (Classification, Face Recognition, Detection and Segmentation). On ImageNet classification, DRConv-based ShuffleNetV2-0.5x achieves state-of-the-art performance of 67.1% at 46M multiply-adds level with 6.3% relative improvement.