# Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation

arXiv: https://arxiv.org/abs/1910.02940 · HTML: https://mlsanity.com/paper/1910.02940/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 29 of 29)

- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [K-Net: Towards Unified Image Segmentation](https://mlsanity.com/paper/2106.14855/) (2021)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Focal Sparse Convolutional Networks for 3D Object Detection](https://mlsanity.com/paper/2204.12463/) (2022)
- [AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement](https://mlsanity.com/paper/2204.13983/) (2022)
- [Adaptive Rotated Convolution for Rotated Object Detection](https://mlsanity.com/paper/2303.07820/) (2023)
- [SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation](https://mlsanity.com/paper/2104.10325/) (2021)
- [MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition](https://mlsanity.com/paper/2306.03445/) (2023)
- [AGConv: Adaptive Graph Convolution on 3D Point Clouds](https://mlsanity.com/paper/2206.04665/) (2022)
- [DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers](https://mlsanity.com/paper/2109.10060/) (2021)
- [Sampling Equivariant Self-attention Networks for Object Detection in Aerial Images](https://mlsanity.com/paper/2111.03420/) (2021)
- [Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation](https://mlsanity.com/paper/2308.04952/) (2023)
- [One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems](https://mlsanity.com/paper/2312.09997/) (2023)
- [NUC-Net: Non-uniform Cylindrical Partition Network for Efficient LiDAR Semantic Segmentation](https://mlsanity.com/paper/2505.24634/) (2025)
- [Learning Modality-Aware Representations: Adaptive Group-wise Interaction Network for Multimodal MRI Synthesis](https://mlsanity.com/paper/2411.14684/) (2024)
- [Integrating Large Circular Kernels into CNNs through Neural Architecture Search](https://mlsanity.com/paper/2107.02451/) (2021)
- [GMConv: Modulating Effective Receptive Fields for Convolutional Kernels](https://mlsanity.com/paper/2302.04544/) (2023)
- [SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis](https://mlsanity.com/paper/2605.07287/) (2026)
- [Log-Polar Space Convolution for Convolutional Neural Networks](https://mlsanity.com/paper/2107.11943/) (2021)
- [End-to-End Adaptive Monte Carlo Denoising and Super-Resolution](https://mlsanity.com/paper/2108.06915/) (2021)
- [Switchable Representation Learning Framework with Self-compatibility](https://mlsanity.com/paper/2206.08289/) (2022)
- [DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors](https://mlsanity.com/paper/2311.17098/) (2023)
- [Removing Multiple Hybrid Adverse Weather in Video via a Unified Model](https://mlsanity.com/paper/2503.06200/) (2025)
- [DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework](https://mlsanity.com/paper/2107.09909/) (2021)
- [SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers](https://mlsanity.com/paper/2308.07110/) (2023)
- [Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels](https://mlsanity.com/paper/2410.22139/) (2024)
- [PARF-Net: integrating pixel-wise adaptive receptive fields into hybrid Transformer-CNN network for medical image segmentation](https://mlsanity.com/paper/2501.02882/) (2025)
- [Intriguing Properties of Dynamic Sampling Networks](https://mlsanity.com/paper/2511.20800/) (2025)
- [Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators](https://mlsanity.com/paper/2512.04705/) (2025)

## Abstract (arXiv)

Convolutional networks are not aware of an object's geometric variations, which leads to inefficient utilization of model and data capacity. To overcome this issue, recent works on deformation modeling seek to spatially reconfigure the data towards a common arrangement such that semantic recognition suffers less from deformation. This is typically done by augmenting static operators with learned free-form sampling grids in the image space, dynamically tuned to the data and task for adapting the receptive field. Yet adapting the receptive field does not quite reach the actual goal -- what really matters to the network is the "effective" receptive field (ERF), which reflects how much each pixel contributes. It is thus natural to design other approaches to adapt the ERF directly during runtime. In this work, we instantiate one possible solution as Deformable Kernels (DKs), a family of novel and generic convolutional operators for handling object deformations by directly adapting the ERF while leaving the receptive field untouched. At the heart of our method is the ability to resample the original kernel space towards recovering the deformation of objects. This approach is justified with theoretical insights that the ERF is strictly determined by data sampling locations and kernel values. We implement DKs as generic drop-in replacements of rigid kernels and conduct a series of empirical studies whose results conform with our theories. Over several tasks and standard base models, our approach compares favorably against prior works that adapt during runtime. In addition, further experiments suggest a working mechanism orthogonal and complementary to previous works.