Pith. sign in

REVIEW 9 cited by

DETRs Beat YOLOs on Real-time Object Detection

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 2304.08069 v3 pith:MIKDTQG3 submitted 2023-04-17 cs.CV

Yian Zhao , Wenyu Lv , Shangliang Xu , Jinman Wei , Guanzhong Wang , Qingqing Dang , Yi Liu , Jie Chen This is my paper
classification cs.CV
keywords accuracyspeedreal-timedetectionimprovingobjectrt-detrrt-detr-r50
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The YOLO series has become the most popular framework for real-time object detection due to its reasonable trade-off between speed and accuracy. However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS. Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. We build RT-DETR in two steps, drawing on the advanced DETR: first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy. Specifically, we design an efficient hybrid encoder to expeditiously process multi-scale features by decoupling intra-scale interaction and cross-scale fusion to improve speed. Then, we propose the uncertainty-minimal query selection to provide high-quality initial queries to the decoder, thereby improving accuracy. In addition, RT-DETR supports flexible speed tuning by adjusting the number of decoder layers to adapt to various scenarios without retraining. Our RT-DETR-R50 / R101 achieves 53.1% / 54.3% AP on COCO and 108 / 74 FPS on T4 GPU, outperforming previously advanced YOLOs in both speed and accuracy. We also develop scaled RT-DETRs that outperform the lighter YOLO detectors (S and M models). Furthermore, RT-DETR-R50 outperforms DINO-R50 by 2.2% AP in accuracy and about 21 times in FPS. After pre-training with Objects365, RT-DETR-R50 / R101 achieves 55.3% / 56.2% AP. The project page: https://zhao-yian.github.io/RTDETR.

Discussion (0). Sign in 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 235 citations worldwide. Full citation record

  1. VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection

    cs.GR 2025-06 conditional novelty 6.0 of 10

    VoxDet reformulates 3D semantic occupancy prediction as dense object detection by deriving instance-boundary offsets from voxel class labels, and reports new state-of-the-art results on camera and LiDAR benchmarks.

  2. 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.

  3. VisAlgae 2023: A Dataset and Challenge for Algae Detection in Microscopy Images

    cs.CV 2025-05 conditional novelty 5.0 of 10

    The VisAlgae 2023 dataset and challenge provide a new public benchmark for detecting six microalgae species in microscopy images, with baseline and top-10 leaderboard results.

  4. Embodied Active Learning under Limited Annotation and Navigation Budget for Object Detection

    cs.RO 2026-07 conditional novelty 4.0 of 10

    A spatial-consistency score—the Prediction Discrepancy—guides both robot navigation and image selection, improving object-detector adaptation under navigation and annotation budgets.

  5. SKGE-SWIN: End-To-End Autonomous Vehicle Waypoint Prediction and Navigation Using Skip Stage Swin Transformer

    cs.CV 2025-08 reject novelty 4.0 of 10

    Adding skip connections between Swin Transformer stages raises the CARLA Driving Score of the authors' end-to-end driving model from 29.7 (x13 CNN baseline) to 37.1 on Town05, in a single reported evaluation run.

  6. Real-Time Beach Litter Detection and Counting: A Comparative Analysis of RT-DETR Model Variants

    cs.CV 2025-08 conditional novelty 4.0 of 10

    On a coastal debris dataset, the smaller RT-DETR-L model detects litter almost as accurately as RT-DETR-X while running about 70 percent faster, making it the more practical deployment choice.

  7. Few-Shot Learning in Video and 3D Object Detection: A Survey

    cs.CV 2025-07 conditional novelty 3.0 of 10

    A survey of few-shot learning for video and 3D object detection that reviews architectures, losses, and training strategies, but contains numerous citation errors and unsupported performance claims.

  8. Open-Vocabulary Object Detection in UAV Imagery: A Review and Future Perspectives

    cs.CV 2025-07 conditional novelty 3.0 of 10

    A structured review that divides aerial open-vocabulary detection methods into pseudo-labeling and CLIP-driven integration families and catalogs the missing benchmarks in the field.

  9. SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning

    cs.LG 2025-08 unverdicted novelty 2.0 of 10

    The submitted body is an unrelated survey, not the SHeRL-FL method claimed in the metadata.

Pith tools