Real-Time Object Detection Meets DINOv3

• URL: http://arxiv.org/abs/2509.20787v2
• Date: Fri, 26 Sep 2025 02:12:39 GMT
• Title: Real-Time Object Detection Meets DINOv3
• Authors: Shihua Huang, Yongjie Hou, Longfei Liu, Xuanlong Yu, Xi Shen,
• Abstract summary: We extend DEIM with DINOv3 features, resulting in DEIMv2.<n>For the X, L, M, and S variants, we adopt DINOv3-pretrained or distilled backbones.<n>For ultra-lightweight models (Nano, Pico, Femto, and Atto), we employ HGNetv2 with depth and width pruning to meet strict resource budgets.
• Score: 8.019044284725
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Benefiting from the simplicity and effectiveness of Dense O2O and MAL, DEIM has become the mainstream training framework for real-time DETRs, significantly outperforming the YOLO series. In this work, we extend it with DINOv3 features, resulting in DEIMv2. DEIMv2 spans eight model sizes from X to Atto, covering GPU, edge, and mobile deployment. For the X, L, M, and S variants, we adopt DINOv3-pretrained or distilled backbones and introduce a Spatial Tuning Adapter (STA), which efficiently converts DINOv3's single-scale output into multi-scale features and complements strong semantics with fine-grained details to enhance detection. For ultra-lightweight models (Nano, Pico, Femto, and Atto), we employ HGNetv2 with depth and width pruning to meet strict resource budgets. Together with a simplified decoder and an upgraded Dense O2O, this unified design enables DEIMv2 to achieve a superior performance-cost trade-off across diverse scenarios, establishing new state-of-the-art results. Notably, our largest model, DEIMv2-X, achieves 57.8 AP with only 50.3 million parameters, surpassing prior X-scale models that require over 60 million parameters for just 56.5 AP. On the compact side, DEIMv2-S is the first sub-10 million model (9.71 million) to exceed the 50 AP milestone on COCO, reaching 50.9 AP. Even the ultra-lightweight DEIMv2-Pico, with just 1.5 million parameters, delivers 38.5 AP, matching YOLOv10-Nano (2.3 million) with around 50 percent fewer parameters. Our code and pre-trained models are available at https://github.com/Intellindust-AI-Lab/DEIMv2

Related papers

• STResNet & STYOLO : A New Family of Compact Classification and Object Detection Models for MCUs [3.9048771791853816]
  STResNet for image classification and STYOLO for object detection jointly optimized for accuracy, efficiency, and memory footprint on resource constrained platforms.<n> STResNetMilli attains 70.0 percent Top 1 accuracy with only three million parameters, outperforming MobileNetV1 and ShuffleNetV2 at comparable computational complexity.
  arXiv  Detail & Related papers  (2026-01-08T20:39:50Z)
• DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning [94.62097655403683]
  We propose DrivePI, a novel spatial-aware 4D MLLM that serves as a unified Vision-Language-Action framework.<n>Our method jointly performs spatial understanding, 3D perception, prediction (i.e., occupancy flow), and planning (i.e., action outputs) in parallel.<n>With only a 0.5B Qwen2.5 model as MLLM backbone, DrivePI as a single unified model matches or exceeds both existing VLA models and specialized VA models.
  arXiv  Detail & Related papers  (2025-12-14T18:45:54Z)
• Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs [111.69640966866059]
  Sparse large language models (LLMs) with Mixture of Experts (MoE) and close to a trillion parameters are dominating the realm of most capable language models.<n>In this paper, we aim to uncover a recipe to harness such scale on Ascend NPUs.<n>The key goals are better usage of the computing resources under the dynamic sparse model structures and materializing the expected performance gain on the actual hardware.
  arXiv  Detail & Related papers  (2025-05-07T15:46:36Z)
• A Light Perspective for 3D Object Detection [46.23578780480946]
  This paper introduces a novel approach that incorporates cutting-edge Deep Learning techniques into the feature extraction process.<n>Our model, NextBEV, surpasses established feature extractors like ResNet50 and MobileNetV3.<n>By fusing these lightweight proposals, we have enhanced the accuracy of the VoxelNet-based model by 2.93% and improved the F1-score of the PointPillar-based model by approximately 20%.
  arXiv  Detail & Related papers  (2025-03-10T10:03:23Z)
• EMOv2: Pushing 5M Vision Model Frontier [92.21687467702972]
  We set up the new frontier of the 5M magnitude lightweight model on various downstream tasks.<n>Our work rethinks the lightweight infrastructure of efficient IRB and practical components in Transformer.<n>Considering the imperceptible latency for mobile users when downloading models under 4G/5G bandwidth, we investigate the performance upper limit of lightweight models with a magnitude of 5M.
  arXiv  Detail & Related papers  (2024-12-09T17:12:22Z)
• Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection [23.464027681439706]
  Grounding DINO 1.5 is a suite of advanced open-set object detection models developed by IDEA Research. Grounding DINO 1.5 Pro is a high-performance model designed for stronger generalization capability across a wide range of scenarios. Grounding DINO 1.5 Edge is an efficient optimized model for faster speed demanded in many applications requiring edge deployment.
  arXiv  Detail & Related papers  (2024-05-16T17:54:15Z)
• YOLO-TLA: An Efficient and Lightweight Small Object Detection Model based on YOLOv5 [19.388112026410045]
  YOLO-TLA is an advanced object detection model building on YOLOv5. We first introduce an additional detection layer for small objects in the neck network pyramid architecture. This module uses sliding window feature extraction, which effectively minimizes both computational demand and the number of parameters.
  arXiv  Detail & Related papers  (2024-02-22T05:55:17Z)
• SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation [83.18930314027254]
  Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion capture with numerous applications. In this work, we investigate scaling up EHPS towards the first generalist foundation model (dubbed SMPLer-X) with up to ViT-Huge as the backbone. With big data and the large model, SMPLer-X exhibits strong performance across diverse test benchmarks and excellent transferability to even unseen environments.
  arXiv  Detail & Related papers  (2023-09-29T17:58:06Z)
• EdgeYOLO: An Edge-Real-Time Object Detector [69.41688769991482]
  This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS 2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone 2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia
  arXiv  Detail & Related papers  (2023-02-15T06:05:14Z)
• EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications [68.35683849098105]
  We introduce split depth-wise transpose attention (SDTA) encoder that splits input tensors into multiple channel groups. Our EdgeNeXt model with 1.3M parameters achieves 71.2% top-1 accuracy on ImageNet-1K. Our EdgeNeXt model with 5.6M parameters achieves 79.4% top-1 accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-06-21T17:59:56Z)
• EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm [111.17100512647619]
  This paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) We propose a novel pyramid EATFormer backbone that only contains the proposed EA-based transformer (EAT) block. Massive quantitative and quantitative experiments on image classification, downstream tasks, and explanatory experiments demonstrate the effectiveness and superiority of our approach.
  arXiv  Detail & Related papers  (2022-06-19T04:49:35Z)
• PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices [13.62426382827205]
  PP-PicoDet family of real-time object detectors achieves superior performance on object detection for mobile devices. Models achieve better trade-offs between accuracy and latency compared to other popular models.
  arXiv  Detail & Related papers  (2021-11-01T12:53:17Z)
• YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs [14.85882314822983]
  In order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to compress such models significantly. In this paper, we propose a novel edge GPU friendly module for multi-scale feature interaction. We also propose a novel learning backbone adoption inspired by the changing translational information flow across various tasks.
  arXiv  Detail & Related papers  (2021-10-26T14:02:59Z)

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.