May 26, 2020
We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression procedure or anchor generation that explicitly encode our prior knowledge about the task. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss that forces unique predictions via bipartite matching, and a transformer encoder-decoder architecture. Given a fixed small set of learned object queries, DETR reasons about the relations of the objects and the global image context to directly output the final set of predictions in parallel. The new model is conceptually simple and does not require a specialized library, unlike many other modern detectors. DETR demonstrates accuracy and run-time performance on par with the well-established and highly-optimized Faster RCNN baseline on the challenging COCO object detection dataset. Moreover, DETR can be easily generalized to produce panoptic segmentation in a unified manner. We show that it significantly outperforms competitive baselines. Training code and pretrained models are available at https://github.com/facebookresearch/detr
Written by
Nicolas Carion
Alexander Kirillov
Francisco Massa
Sergey Zagoruyko
Publisher
ECCV
Research Topics
March 09, 2023
Bilal Porgali, VĂtor Albiero, Jordan Ryda, Cristian Canton Ferrer, Caner Hazirbas
March 09, 2023
February 21, 2023
Felix Xu, Fuyuan Zhang, Hua Qi, Jianjun Zhao, Jianlang Chen, Lei Ma, Qing Guo, Zhijie Wang
February 21, 2023
January 10, 2023
Gokhan Uzunbas, Joena Zhang, Sara Cao, Ser-Nam Lim, Taipeng Tian, Bohyung Han, Seonguk Seo
January 10, 2023
January 04, 2023
Xi Liu, Panganamala Kumar, Ruida Zhou, Tao Liu
January 04, 2023