Deformable DETR: Deformable Transformers for End-to-End Object Detection

October 08, 2020 · Entered Twilight · 🏛 International Conference on Learning Representations

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, benchmark.py, configs, datasets, docs, engine.py, figs, main.py, models, requirements.txt, tools, util

Authors Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, Jifeng Dai arXiv ID 2010.04159 Category cs.CV: Computer Vision Citations 6.8K Venue International Conference on Learning Representations Repository https://github.com/fundamentalvision/Deformable-DETR ⭐ 3895 Last Checked 1 month ago

Abstract

DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10 times less training epochs. Extensive experiments on the COCO benchmark demonstrate the effectiveness of our approach. Code is released at https://github.com/fundamentalvision/Deformable-DETR.