TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/Deformable DETR

Deformable DETR

Computer VisionIntroduced 200035 papers
Source Paper

Description

Deformable DETR is an object detection method that aims mitigates the slow convergence and high complexity issues of DETR. It combines the best of the sparse spatial sampling of deformable convolution, and the relation modeling capability of Transformers. Specifically, it introduces a deformable attention module, which attends to a small set of sampling locations as a pre-filter for prominent key elements out of all the feature map pixels. The module can be naturally extended to aggregating multi-scale features, without the help of FPN.

Papers Using This Method

WalnutData: A UAV Remote Sensing Dataset of Green Walnuts and Model Evaluation2025-02-27SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection2024-12-28Advancing SEM Based Nano-Scale Defect Analysis in Semiconductor Manufacturing for Advanced IC Nodes2024-09-06U-DECN: End-to-End Underwater Object Detection ConvNet with Improved DeNoising Training2024-08-11Fisher-aware Quantization for DETR Detectors with Critical-category Objectives2024-07-03Understanding differences in applying DETR to natural and medical images2024-05-27Infrared Adversarial Car Stickers2024-05-16Generative Region-Language Pretraining for Open-Ended Object Detection2024-03-15KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling2024-01-01Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective2024-01-01Mono3DVG: 3D Visual Grounding in Monocular Images2023-12-13Towards Few-Annotation Learning for Object Detection: Are Transformer-based Models More Efficient ?2023-10-30DAC-DETR: Divide the Attention Layers and Conquer2023-09-21Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection2023-05-18Robust Traffic Light Detection Using Salience-Sensitive Loss: Computational Framework and Evaluations2023-05-08Continual Detection Transformer for Incremental Object Detection2023-04-06VDDT: Improving Vessel Detection with Deformable Transfomer2023-03-15Salient Sign Detection In Safe Autonomous Driving: AI Which Reasons Over Full Visual Context2023-01-14Open World DETR: Transformer based Open World Object Detection2022-12-06FQDet: Fast-converging Query-based Detector2022-10-05