RESEARCH

COMPUTER VISION

End-to-end object detection with Transformers

May 26, 2020

Abstract

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

Download the Paper

AUTHORS

Written by

Nicolas Carion

Alexander Kirillov

Francisco Massa

Gabriel Synnaeve

Nicolas Usunier

Sergey Zagoruyko

Publisher

ECCV

Research Topics

Computer Vision

Related Publications

December 15, 2021

RESEARCH

Sample-and-threshold differential privacy: Histograms and applications

Akash Bharadwaj, Graham Cormode

December 15, 2021

December 06, 2021

COMPUTER VISION

CORE MACHINE LEARNING

Debugging the Internals of Convolutional Networks

Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani, Shubham Muttepawar, Edward Wang (AI Infra), Sara Zhang, David Adkins, Orion Reblitz-Richardson

December 06, 2021

December 06, 2021

COMPUTER VISION

Early Convolutions Help Transformers See Better

Tete Xiao, Mannat Singh, Eric Mintun, Trevor Darrell, Piotr Dollar, Ross Girshick

December 06, 2021

November 09, 2021

COMPUTER VISION

CORE MACHINE LEARNING

Grounding inductive biases in natural images: invariance stems from variations in data

Diane Bouchacourt, Mark Ibrahim, Ari Morcos

November 09, 2021