Team DETR: Guide Queries as a Professional Team in Detection Transformers
Tian Qiu, Linyun Zhou, Wenxiang Xu, Lechao Cheng, Zunlei Feng, Mingli, Song

TL;DR
Team DETR introduces a collaborative query mechanism with position constraints to improve object detection accuracy, especially for small and large objects, without increasing model complexity.
Contribution
It proposes a novel query collaboration and position constraint method that enhances DETR's detection performance and adaptability without additional parameters.
Findings
Significant performance improvements on COCO dataset.
Enhanced detection of small and large objects.
Flexible integration with existing DETR variants.
Abstract
Recent proposed DETR variants have made tremendous progress in various scenarios due to their streamlined processes and remarkable performance. However, the learned queries usually explore the global context to generate the final set prediction, resulting in redundant burdens and unfaithful results. More specifically, a query is commonly responsible for objects of different scales and positions, which is a challenge for the query itself, and will cause spatial resource competition among queries. To alleviate this issue, we propose Team DETR, which leverages query collaboration and position constraints to embrace objects of interest more precisely. We also dynamically cater to each query member's prediction preference, offering the query better scale and spatial priors. In addition, the proposed Team DETR is flexible enough to be adapted to other existing DETR variants without increasing…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsData Management and Algorithms · Anomaly Detection Techniques and Applications · Automated Road and Building Extraction
MethodsMulti-Head Attention · Attention Is All You Need · Layer Normalization · Linear Layer · Label Smoothing · Absolute Position Encodings · Adam · Position-Wise Feed-Forward Layer · Softmax · Residual Connection
