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

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... (read more)

PDF Abstract ICLR 2021 PDF (under review) ICLR 2021 Abstract (under review)

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Object Detection COCO test-dev Deformable DETR (ResNeXt-101+DCN) box AP 52.3 # 11
AP50 71.9 # 9
AP75 58.1 # 10
APS 34.4 # 12
APM 54.4 # 17
APL 65.6 # 9

Methods used in the Paper