How to Backpropagate through Hungarian in Your DETR?
원문 초록
The DEtection TRansformer (DETR) approach, which uses a transformer encoder-decoder architecture and a set-based global loss, has become a building block in many transformer based applications. However, as originally presented, the assignment cost and the global loss are not aligned, i.e., reducing the former is likely but not guaranteed to reduce the latter. And the issue of gradient is ignored when a combinatorial solver such as Hungarian is used. In this paper we show that the global loss can be expressed as the sum of an assignment-independent term, and an assignment-dependent term which can be used to define the assignment cost matrix. Recent results on generalized gradients of optimal assignment cost with respect to parameters of an assignment problem are then used to define generalized gradients of the loss with respect to network parameters, and backpropagation is carried out properly. Our experiments using the same loss weights show interesting convergence properties and a potential for further performance improvements.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
Making Language Model a Hierarchical Classifier and Generator
Seq vs Seq: An Open Suite of Paired Encoders and Decoders
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
$I^{2}$-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting
Real-Time ESFP: Estimating, Smoothing, Filtering, and Pose-Mapping
토론
이 논문과 연결된 포럼 글이 아직 없습니다.