Timezone: »
Recently, two-stage Deformable DETR introduced the query-based two-stage head, a new type of two-stage head different from the region-based two-stage heads of classical detectors as Faster R-CNN. In query-based two-stage heads, the second stage selects one feature per detection processed by a transformer, called the query, as opposed to pooling a rectangular grid of features processed by CNNs as in region-based detectors. In this work, we improve the query-based head by improving the prior of the cross-attention operation with anchors, significantly speeding up the convergence while increasing its performance. Additionally, we empirically show that by improving the cross-attention prior, auxiliary losses and iterative bounding box mechanisms typically used by DETR-based detectors are no longer needed. By combining the best of both the classical and the DETR-based detectors, our FQDet head peaks at 45.4 AP on the 2017 COCO validation set when using a ResNet-50+TPN backbone, only after training for 12 epochs using the 1x schedule. We outperform other high-performing two-stage heads such as e.g. Cascade R-CNN, while using the same backbone and while being computationally cheaper. Additionally, when using the large ResNeXt-101-DCN+TPN backbone and multi-scale testing, our FQDet head achieves 52.9 AP on the 2017 COCO test-dev set after only 12 epochs of training. Code will be released.
Author Information
Cédric Picron (KU Leuven)
Punarjay Chakravarty (Ford Motor Company)
Tinne Tuytelaars (KU Leuven)
More from the Same Authors
-
2022 : Panel »
Tyler Hayes · Tinne Tuytelaars · Subutai Ahmad · João Sacramento · Zsolt Kira · Hava Siegelmann · Christopher Summerfield -
2019 Poster: Online Continual Learning with Maximal Interfered Retrieval »
Rahaf Aljundi · Eugene Belilovsky · Tinne Tuytelaars · Laurent Charlin · Massimo Caccia · Min Lin · Lucas Page-Caccia -
2017 Poster: Pose Guided Person Image Generation »
Liqian Ma · Xu Jia · Qianru Sun · Bernt Schiele · Tinne Tuytelaars · Luc Van Gool -
2016 Poster: Dynamic Filter Networks »
Xu Jia · Bert De Brabandere · Tinne Tuytelaars · Luc V Gool