The reviewed record of science sign in
Pith

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

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

Zhuyu Yao , Jiangbo Ai , Boxun Li , Chi Zhang This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:CIHPMTKJrecord.jsonopen to challenge →

classification cs.CV
keywords objectdetrefficientdecoderdetectiondenseend-to-endstructure
0
0 comments X
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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing

    cs.CV 2026-06 unverdicted novelty 6.0

    SegFS is a dual-path architecture that uses sparse keyframe open-vocabulary predictions to condition a fast feature-space network for efficient temporal instance segmentation in videos.

  2. Modular Diffusion Models for Structured Visual Recognition

    cs.CV 2026-06 unverdicted novelty 6.0

    Modular Diffusion Models decompose diffusion into task-specific modules to model distributions over structured visual outputs for detection, segmentation, and scene graph generation.

  3. SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection

    cs.CV 2026-05 unverdicted novelty 6.0

    SToRe3D delivers up to 3x faster inference for multi-view 3D object detection in ViTs by selecting relevant 2D tokens and 3D queries via mutual relevance heads with only marginal accuracy loss.

  4. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

    cs.CV 2022-03 conditional novelty 6.0

    DINO reaches 51.3 AP on COCO val2017 with a ResNet-50 backbone after 24 epochs, a +2.7 AP gain over the prior best DETR variant.

  5. Hippocampus-DETR: An Explicit Memory Object Detection Framework Based on Hippocampus Modeling

    cs.CV 2026-06 unverdicted novelty 5.0

    Hippocampus-DETR integrates a hippocampal memory network (HipNet) into DETR to simulate brain subregions for pattern separation, completion, and improved detection accuracy plus generalization.