Deformable Attention

Follow this topic Ask about this topic

Deformable attention studies how models can learn sparse, input-dependent sampling locations, making attention more efficient and better aligned with objects, motion, or geometry. Common approaches include multi-scale deformable attention in detection transformers, offset-based feature alignment for multimodal inputs, and sparse spatiotemporal attention for video and 3D tasks. These methods are used in settings such as object detection, segmentation, occupancy prediction, and robotics, where fixed grids or dense attention can be costly or miss important local structure. A central challenge is balancing reduced computation with reliable sampling, especially when scenes, modalities, or motion patterns differ from training data.

Latest papers

13 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

ACorD: Adaptive Correspondence Discovery for Medical Image Registration
Oct 19, 2026Arghavan Rezvani, Kun Han, Xiaohui XieMedical Image Registration Deformable Image Registration
University of California, Irvine
DELTA: Deformable Elevation-Based Local Terrain Attention Encoder for Sparse-Terrain Quadrupedal Locomotion
Aug 22, 2026Sanghyun Park, Moonkyu Jung, Jemin HwangboTerrain-Aware Robot Locomotion Robot Locomotion
Robotics and Artificial Intelligence Lab, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon 34141, Republic of Korea
MegaSlide-DiT: Memory-Centric Adaptation and Deformable Local Attention for Efficient Video Diffusion
Jul 17, 2026Jiacheng Liu, Jason LiuVideo Diffusion Models Diffusion Transformer
Trendinsight Lab / UC San Diego
GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
Jul 1, 2026Siwoo Lim, Sunjae Yoon, Gwanhyeong Koo +1Multi-View Consistency 3D Gaussian Splatting
Korea Advanced Institute of Science and Technology (KAIST), Republic of Korea · Chung-Ang University, Republic of Korea
Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection
Jun 23, 2026Tian Qiu, Jifeng Shen, Xin ZuoCross-Modal Attention Cross-Modal Alignment
School of Electrical and Information Engineering, Jiangsu University, Zhenjiang, 212013, China · School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang, 212003, China
Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting
Jun 17, 2026Hao-Yuan Ma, Li Zhang, Yushi Qiu +3Crowd Counting Deformable Attention
School of Computer Science and Technology, Soochow University, Suzhou, China
Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks
Jun 1, 2026Nermeen Abou Baker, David Rohrschneider, Uwe HandmannFine-Tuning Instance Segmentation
Ruhr West University of applied sciences · Lützowstraße 5, 46236 Bottrop, Germany: Ruhr West University of Applied Sciences
VigilFormer: Deformable Attention for Video Anomaly Detection with Causal Risk Inference
May 31, 2026Xinze ZhangTransformer Attention Deformable Attention
University of Southern California, Los Angeles, CA 90007, USA
VGGT-Occ: Geometry-Grounded and Density-Aware Gated Fusion for 3D Occupancy Prediction
May 16, 2026Xun Chen, Tianchen Deng, Rui Wang +53D Semantic Segmentation 3D Occupancy Prediction
Nanyang Technological University · Shanghai Jiao Tong University · ETH Zurich
Towards Open World Sound Event Detection
May 5, 2026P. H. Hai, L. T. Minh, L. H. SonContinual Learning Detection Transformer
VNU University of Engineering and Technology, Hanoi, 100000, Vietnam · Artificial Intelligence Research Center, VNU Information Technology Institute, Hanoi, 100000, Vietnam
CAM3DNet: Comprehensively mining the multi-scale features for 3D Object Detection with Multi-View Cameras
Apr 18, 2026Mingxi Pang, Dingheng Wang, Zekun Li +4Multi-Scale Feature Fusion Multi-View 3D Object Detection
College of Intelligent Science and Technology, National University of Defense Technology, Changsha, 410073, China · Northwest Institute of Mechanical & Electrical Engineering, Xianyang, 712099, China. · School of Aerospace Engineering, Xi’an Jiaotong University, Xi’an, 710049, China
A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection
Mar 13, 2026Matteo Rossi, Pony MattDetection Transformer Industrial Inspection
Maharaja Agrasen University
DiDA: Video Object Segmentation with Distillation Learning of Deformable Attention
Jan 25, 2024Quang-Trung Truong, Duc Thanh Nguyen, Binh-Son Hua +1Video Object Segmentation Transformer Attention
Hong Kong University of Science and Technology · Deakin University · Trinity College Dublin

Oct 19, 2026J/K move · Enter open · S save

ACorD: Adaptive Correspondence Discovery for Medical Image Registration

Arghavan Rezvani, Kun Han, Xiaohui Xie

University of California, Irvine

Medical Image Registration Deformable Image Registration Deformable Attention

Open paper AskPDF arXiv

Medical image registration is a fundamental task for aligning anatomical structures across images. Exhaustively searching for point-wise correspondences is prohibitively expensive in both computation and memory, particularly for high-resolution 3D medical images. Most recent learning-based methods directly predict correspondences in a coarse-to-fine manner, but often propagate intermediate estimates across scales without explicitly weighting correspondence evidence, which can allow coarse-scale errors to persist during refinement. To address these challenges, we propose ACorD, an adaptive correspondence discovery framework designed to mitigate error propagation with an attention-guided process. ACorD first predicts multiple potential correspondence candidates through Correlation-guided Cross-scale Offset Prediction (CCOP), which combines correlation maps as spatial matching priors with cross-scale features as global deformation context. Then, Multi-Head Deformable Aggregation (MHDA) aggregates these candidate correspondences using attention, producing a learned, non-uniform weighting over competing matches rather than treating them equally. The multi-head design further captures complementary deformation patterns, ensuring both global alignment and local precision. By integrating adaptive offset prediction with selective, attention-based aggregation of correspondence evidence, ACorD enables accurate deformation refinement. Extensive experiments on four public medical registration benchmarks demonstrate that adaptive correspondence discovery within a multi-scale refinement framework improves registration robustness across diverse anatomical structures.