A Aligned-Matching DEtection TRansformer
Accelerating DETR Convergence via Semantic-Aligned Matching
We present a semantic-aligned-matching (sam-detr) detector that greatly accelerates the convergence of the recently developed detection transformer (detr) without sacrificing its accuracy.The proposed sam-detr addresses the convergence issue from two perspectives.First, it projects object queries into the same embeddingspace as encoded image features, where the matching can be accomplished efficiently with aligned semantics.Second, it explicitly searches salient points with the most discriminative features for semantic-aligned matching, which further speeds up the convergence and boosts detection accuracy as well.Being like a plug and play, sam-detr complements existing convergence solutions well yet only introduces slight computational overhead.Extensive experiments show that the proposed sam-detr achieves superior convergence as well as competitive detection accuracy.
