Pith. sign in

REVIEW 1 cited by

Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2112.13310 v1 pith:ULND5FDO submitted 2021-12-26 cs.CV

classification cs.CV
keywords self-attentiondetectionmiti-detrnetworkobjecttransformerattentionarchitecture
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Object Detection with Transformers (DETR) and related works reach or even surpass the highly-optimized Faster-RCNN baseline with self-attention network architectures. Inspired by the evidence that pure self-attention possesses a strong inductive bias that leads to the transformer losing the expressive power with respect to network depth, we propose a transformer architecture with a mitigatory self-attention mechanism by applying possible direct mapping connections in the transformer architecture to mitigate the rank collapse so as to counteract feature expression loss and enhance the model performance. We apply this proposal in object detection tasks and develop a model named Miti-DETR. Miti-DETR reserves the inputs of each single attention layer to the outputs of that layer so that the "non-attention" information has participated in any attention propagation. The formed residual self-attention network addresses two critical issues: (1) stop the self-attention networks from degenerating to rank-1 to the maximized degree; and (2) further diversify the path distribution of parameter update so that easier attention learning is expected. Miti-DETR significantly enhances the average detection precision and convergence speed towards existing DETR-based models on the challenging COCO object detection dataset. Moreover, the proposed transformer with the residual self-attention network can be easily generalized or plugged in other related task models without specific customization.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse

    cs.LG 2025-05 reject novelty 4.0 of 10

    A residual self-attention network with all weight entries bounded by a small η can be approximated by one layer to error O(η)‖X‖∞, so skip connections do not prevent layer collapse.

Pith tools