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

May 3, 2021

Speakers

About

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 shall be released.

Organizer

Categories

About ICLR 2021

The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.

Store presentation

Should this presentation be stored for 1000 years?

How do we store presentations

Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%

Sharing

Recommended Videos

Presentations on similar topic, category or speaker

Interested in talks like this? Follow ICLR 2021