MDS-DETR: DETR with Masked Duplicate Suppressor

• URL: http://arxiv.org/abs/2605.23507v1
• Date: Fri, 22 May 2026 11:10:17 GMT
• Title: MDS-DETR: DETR with Masked Duplicate Suppressor
• Abstract summary: Masked Duplicate Suppressor (MDS) injects asymmetry into self-attention via confidence-based causal masking.<n>MDS-DETR outperforms existing one-to-many DETR variants such as MS-DETR, MR.DETR and Relation-DETR, without relying on any additional queries or auxiliary decoders.
• Score: 12.073668006425981
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The DEtection TRansformer (DETR) is a powerful end-to-end object detector, yet its one-to-one matching strategy suffers from slow convergence and low recall. A common approach to address this issue is to use one-to-many label assignment to provide more positive samples. However, existing methods that use one-to-many matching as an auxiliary objective lead to increased training costs, with their auxiliary decoders discarded during inference. To address this limitation, we propose MDS-DETR, which leverages both one-to-one and one-to-many supervision within a single decoder. Specifically, we introduce a Masked Duplicate Suppressor (MDS) that injects asymmetry into self-attention via confidence-based causal masking. MDS filters out the duplicates generated by the one-to-many supervised layer, enables explainable, duplicate-free predictions in a fully end-to-end framework. MDS-DETR outperforms existing one-to-many DETR variants such as MS-DETR, MR.DETR and Relation-DETR, without relying on any additional queries or auxiliary decoders. Under a 12-epoch training schedule on MS COCO with a ResNet-50 backbone, MDS-DETR achieves a +2.8 mAP improvement over Deformable-DETR with only a 5\% increase in training time, and outperforms the state-of-the-art MR.DETR by +0.3 mAP while being even 20\% faster in training. Our code and models are available at \href{https://github.com/dcholee/mds-detr}{https://github.com/DChoLee/MDS-DETR}.

Related papers

• DiffGRM: Diffusion-based Generative Recommendation Model [63.35379395455103]
  Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID)<n>We propose DiffGRM, a diffusion-based GR model that replaces the autoregressive decoder with a masked discrete diffusion model (MDM)<n> Experiments show consistent gains over strong generative and discriminative recommendation baselines on multiple datasets.
  arXiv  Detail & Related papers  (2025-10-21T03:23:32Z)
• MS-DETR: Efficient DETR Training with Mixed Supervision [74.93329653526952]
  MS-DETR places one-to-many supervision to the object queries of the primary decoder that is used for inference. Our approach does not need additional decoder branches or object queries. Experimental results show that our approach outperforms related DETR variants.
  arXiv  Detail & Related papers  (2024-01-08T16:08:53Z)
• FeatAug-DETR: Enriching One-to-Many Matching for DETRs with Feature Augmentation [48.94488166162821]
  One-to-one matching is a crucial design in DETR-like object detection frameworks. We propose two methods that realize one-to-many matching from a different perspective of augmenting images or image features. We conduct extensive experiments to evaluate the effectiveness of the proposed approach on DETR variants.
  arXiv  Detail & Related papers  (2023-03-02T18:59:48Z)
• Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion [95.7732308775325]
  The proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection. DETR suffers from slow training convergence, which hinders its applicability to various detection tasks. We design Semantic-Aligned-Matching DETR++ to accelerate DETR's convergence and improve detection performance.
  arXiv  Detail & Related papers  (2022-07-28T15:34:29Z)
• Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment [80.55064790937092]
  One-to-many assignment, assigning one ground-truth object to multiple predictions, succeeds in detection methods such as Faster R-CNN and FCOS. We introduce Group DETR, a simple yet efficient DETR training approach that introduces a group-wise way for one-to-many assignment. Experiments show that Group DETR significantly speeds up the training convergence and improves the performance of various DETR-based models.
  arXiv  Detail & Related papers  (2022-07-26T17:57:58Z)
• DETRs with Hybrid Matching [21.63116788914251]
  One-to-one set matching is a key design for DETR to establish its end-to-end capability. We propose a hybrid matching scheme that combines the original one-to-one matching branch with an auxiliary one-to-many matching branch during training.
  arXiv  Detail & Related papers  (2022-07-26T17:52:14Z)
• A Free Lunch to Person Re-identification: Learning from Automatically Generated Noisy Tracklets [52.30547023041587]
  unsupervised video-based re-identification (re-ID) methods have been proposed to solve the problem of high labor cost required to annotate re-ID datasets. But their performance is still far lower than the supervised counterparts. In this paper, we propose to tackle this problem by learning re-ID models from automatically generated person tracklets.
  arXiv  Detail & Related papers  (2022-04-02T16:18:13Z)
• DN-DETR: Accelerate DETR Training by Introducing Query DeNoising [20.589146395352714]
  We present a novel training method to speedup DETR (DEtection TRansformer) training. We show that the slow convergence results from the instability of bipartite graph matching. Our method feeds ground-truth bounding boxes with noises into Transformer decoder and trains the model to reconstruct the original boxes.
  arXiv  Detail & Related papers  (2022-03-02T18:50:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.