Pith. sign in

REVIEW 18 cited by

DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

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 2201.12329 v4 pith:VD5MSZE5 submitted 2022-01-28 cs.CV

DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR

Shilong Liu , Feng Li , Hao Zhang , Xiao Yang , Xianbiao Qi , Hang Su , Jun Zhu , Lei Zhang This is my paper
classification cs.CV
keywords detrqueriesanchorboxescoordinatesdab-detrdetectiondynamic
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We present in this paper a novel query formulation using dynamic anchor boxes for DETR (DEtection TRansformer) and offer a deeper understanding of the role of queries in DETR. This new formulation directly uses box coordinates as queries in Transformer decoders and dynamically updates them layer-by-layer. Using box coordinates not only helps using explicit positional priors to improve the query-to-feature similarity and eliminate the slow training convergence issue in DETR, but also allows us to modulate the positional attention map using the box width and height information. Such a design makes it clear that queries in DETR can be implemented as performing soft ROI pooling layer-by-layer in a cascade manner. As a result, it leads to the best performance on MS-COCO benchmark among the DETR-like detection models under the same setting, e.g., AP 45.7\% using ResNet50-DC5 as backbone trained in 50 epochs. We also conducted extensive experiments to confirm our analysis and verify the effectiveness of our methods. Code is available at \url{https://github.com/SlongLiu/DAB-DETR}.

discussion (0)

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

Forward citations

Cited by 18 Pith papers

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

  1. MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraints

    cs.CV 2026-06 unverdicted novelty 7.0

    MVDGC unifies BEV and image-view pedestrian localization into one task via 3D cylindrical queries that enforce dual geometric constraints between views.

  2. InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery

    cs.CV 2026-05 conditional novelty 7.0

    InterMesh explicitly incorporates human-object interaction semantics into multi-person mesh recovery via a detector and two lightweight modules, delivering up to 9.9% MPJPE reduction on interaction-heavy datasets.

  3. WUTDet: A 100K-Scale Ship Detection Dataset and Benchmarks with Dense Small Objects

    cs.CV 2026-04 unverdicted novelty 7.0

    WUTDet is a 100K-image ship detection dataset with benchmarks indicating Transformer models outperform CNN and Mamba architectures in accuracy and small-object detection for complex maritime environments.

  4. MoCA3D: Monocular 3D Bounding Box Prediction in the Image Plane

    cs.CV 2026-03 unverdicted novelty 7.0

    MoCA3D formulates monocular 3D box prediction as dense pixel-space tasks using corner heatmaps and depth maps, with a new PAG metric for image-plane evaluation.

  5. Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability

    cs.CV 2026-07 accept novelty 6.0

    A dual-query scene graph generation method unifies detector-based and query-based reasoning in a single decoder, achieving state-of-the-art results on Visual Genome, Open Images v6, and GQA-200.

  6. 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.

  7. 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.

  8. InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery

    cs.CV 2026-05 unverdicted novelty 6.0

    InterMesh improves multi-person human mesh recovery accuracy by explicitly enriching DETR-style queries with structured interaction semantics from a human-object detector.

  9. YOLOv12: Attention-Centric Real-Time Object Detectors

    cs.CV 2025-02 unverdicted novelty 6.0

    YOLOv12 is a new attention-based real-time object detector that reports higher accuracy than YOLOv10, YOLOv11, and RT-DETR variants at comparable or better speed and efficiency.

  10. Excretion Detection in Pigsties Using Convolutional and Transformerbased Deep Neural Networks

    cs.CV 2024-11 unverdicted novelty 6.0

    Four object detection models achieve over 90% average precision detecting excretions in pigsties from thermal images and remain reasonably robust on out-of-distribution data from different barns.

  11. GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization

    cs.CL 2024-10 unverdicted novelty 6.0

    GigaCheck detects LLM-generated text at both document and span levels by combining fine-tuned language-model embeddings with a DETR-like architecture that treats generated intervals as detectable objects.

  12. 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.

  13. CellDETR: A Detection-Guided Framework for Scalable Cell Representation Learning from Histopathology Images

    cs.CV 2026-06 unverdicted novelty 5.0

    CellDETR is a detection-guided framework extending Deformable DETR for cell representation learning from WSIs, with contrastive pretraining and cross-dataset transfer shown on PanNuke and Xenium data.

  14. EIVE: End-to-End Instance-Specific Visual Explanations for Detection Transformers

    cs.CV 2026-06 unverdicted novelty 5.0

    EIVE reformulates decoder cross-attention in Detection Transformers to produce instance-specific saliency maps via cross-layer fusion and attention-aware training, matching post-hoc methods in quality while improving speed.

  15. LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images

    cs.CV 2026-05 unverdicted novelty 5.0

    LangFlash introduces a feed-forward model for 3D language Gaussian splatting from sparse unposed images, claiming superior novel view synthesis and semantic consistency via enriched training data and sparse semantic encoding.

  16. Caries DETR: Tooth Structure-aware Prior and Lesion-aware Dynamic Loss Refinement for DETR Based Caries Detection

    cs.CV 2026-04 unverdicted novelty 5.0

    Caries-DETR adds tooth-structure query initialization and lesion-aware loss reweighting to DETR, reaching state-of-the-art caries detection on AlphaDent and DentalAI datasets.

  17. Visual Accommodation: Rethinking Image Scale as a Learnable Variable for Object Detection

    cs.CV 2024-12 unverdicted novelty 5.0

    Ciliary-DETR adds a learnable scale predictor and parametric loss objectives to enable test-time image scale adjustment for object detection in a single forward pass.

  18. Intra-YOLO: A Small Object Detection Model for Caries and Molar-Incisor Hypomineralization in Intraoral Photography Based on Transfer Learning with Reinforcement Learning

    cs.CV 2026-05 unverdicted novelty 3.0

    Intra-YOLO applies YOLO object detection with transfer learning and reinforcement learning to identify and differentiate caries and MIH in intraoral images.