Pith. sign in

REVIEW 9 cited by

Efficient DETR: Improving End-to-End Object Detector with Dense Prior

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2104.01318 v1 pith:CIHPMTKJ submitted 2021-04-03 cs.CV

Zhuyu Yao , Jiangbo Ai , Boxun Li , Chi Zhang This is my paper · ORCID
classification cs.CV
keywords objectdetrefficientdecoderdetectiondenseend-to-endstructure
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively, without which their performance degrades seriously. In this paper, we investigate that the random initialization of object containers, which include object queries and reference points, is mainly responsible for the requirement of multiple iterations. Based on our findings, we propose Efficient DETR, a simple and efficient pipeline for end-to-end object detection. By taking advantage of both dense detection and sparse set detection, Efficient DETR leverages dense prior to initialize the object containers and brings the gap of the 1-decoder structure and 6-decoder structure. Experiments conducted on MS COCO show that our method, with only 3 encoder layers and 1 decoder layer, achieves competitive performance with state-of-the-art object detection methods. Efficient DETR is also robust in crowded scenes. It outperforms modern detectors on CrowdHuman dataset by a large margin.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 160 citations worldwide. Full citation record

  1. Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Multi-route training with instructive self-attention tokens and a route-aware mixture-of-experts raises detection mAP by 2 to 4 points across several DETR baselines at no inference cost.

  2. FAST-Splat: Fast, Ambiguity-Free Semantics Transfer in Gaussian Splatting

    cs.CV 2024-11 conditional novelty 6.0 of 10

    FAST-Splat stores a 3D semantic code on each Gaussian, trains it jointly with the scene, and uses a hash-table of detected objects to give fast, low-memory open-vocabulary 3D segmentation with disambiguated object labels.

  3. DQEN: Dual Query Enhancement Network for DETR-based HOI Detection

    cs.CV 2025-08 conditional novelty 5.0 of 10

    DQEN enhances DETR-based HOI detection by initializing object and interaction queries with encoder features and CLIP text-derived semantics, improving HICO-Det mAP but not V-COCO.

  4. DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A flexible-query transformer detector that separates cross-attention localization from self-attention deduplication reports consistent accuracy gains over DINO across five backbones.

  5. Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Decoupled PROB combines query selection with learnable queries and stops objectness prediction early in the decoder, improving known-object detection in open-world benchmarks.

  6. Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection

    cs.CV 2025-05 conditional novelty 5.0 of 10

    Cross-DINO improves small-object detection in DETR-like detectors by mixing MLP backbone features, a cross-coding fusion module, and a category-size soft-label loss, achieving 36.4% APs on COCO.

  7. Evaluating the Adversarial Robustness of Detection Transformers

    cs.CV 2024-12 conditional novelty 5.0 of 10

    DETR object detectors are highly vulnerable to standard adversarial attacks, transfer attacks within the DETR family, and a new attack using intermediate losses cuts accuracy with smaller perturbations.

  8. Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset

    cs.CV 2024-12 conditional novelty 5.0 of 10

    MvHeat-DET, a Mixture-of-Experts heat-conduction detector, outperforms 15 re-trained baselines on the new EvDET200K dataset and reaches 55.7 mAP on N-Caltech101.

  9. HiddenObject: Modality-Agnostic Fusion for Multimodal Hidden Object Detection

    cs.CV 2025-08 conditional novelty 4.0 of 10

    A Mamba-based fusion network with a channel-aware decoder reports competitive or state-of-the-art results on RGB-thermal and RGB-depth hidden-object detection benchmarks.

Pith tools