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

Abstract

We present DINO (\textbf{D}ETR with \textbf{I}mproved de\textbf{N}oising anch\textbf{O}r boxes), a state-of-the-art end-to-end object detector. % in this paper. DINO improves over previous DETR-like models in performance and efficiency by using a contrastive way for denoising training, a mixed query selection method for anchor initialization, and a look forward twice scheme for box prediction. DINO achieves $49.4$AP in $12$ epochs and $51.3$AP in $24$ epochs on COCO with a ResNet-50 backbone and multi-scale features, yielding a significant improvement of $\text{+6.0}$\textbf{AP} and $\text{+2.7}$\textbf{AP}, respectively, compared to DN-DETR, the previous best DETR-like model. DINO scales well in both model size and data size. Without bells and whistles, after pre-training on the Objects365 dataset with a SwinL backbone, DINO obtains the best results on both COCO \texttt{val2017} ($\text{63.2}$\textbf{AP}) and \texttt{test-dev} (\textbf{$\text{63.3}$AP}). Compared to other models on the leaderboard, DINO significantly reduces its model size and pre-training data size while achieving better results. Our code will be available at \url{https://github.com/IDEACVR/DINO}.

Cited by in corpus (27)

• UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection
• Physical Adversarial Attack meets Computer Vision: A Decade Survey
• UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility
• A Multi-task Framework for Infrared Small Target Detection and Segmentation
• Oriented object detection in optical remote sensing images using deep learning: a survey
• Autonomous Advanced Aerial Mobility -- An End-to-end Autonomy Framework for UAVs and Beyond
• E${}^3$-UAV: An Edge-based Energy-Efficient Object Detection System for Unmanned Aerial Vehicles
• SpecDETR: A transformer-based hyperspectral point object detection network
• Vehicle Perception from Satellite
• Deep Learning-Based Connector Detection for Robotized Assembly of Automotive Wire Harnesses
• A Multimodal Dataset and Benchmark for Radio Galaxy and Infrared Host Detection
• MS-DETR: Natural Language Video Localization with Sampling Moment-Moment Interaction
• Foundation Model-Based Apple Ripeness and Size Estimation for Selective Harvesting
• Focused Decoding Enables 3D Anatomical Detection by Transformers
• Taming Detection Transformers for Medical Object Detection
• Visual inspection for illicit items in X-ray images using Deep Learning
• Multiple Object Tracking in Video SAR: A Benchmark and Tracking Baseline
• VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond
• Parametric Primitive Analysis of CAD Sketches with Vision Transformer
• ICDAR 2023 Competition on Robust Layout Segmentation in Corporate Documents
• STRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Prediction
• Smelly, dense, and spreaded: The Object Detection for Olfactory References (ODOR) dataset
• OAH-Net: A Deep Neural Network for Hologram Reconstruction of Off-axis Digital Holographic Microscope
• Illicit object detection in X-ray images using Vision Transformers
• Learning Efficient Unsupervised Satellite Image-based Building Damage Detection
• Holi-DETR: Holistic Fashion Item Detection Leveraging Contextual Information
• Wild Berry image dataset collected in Finnish forests and peatlands using drones