OD3: Optimization-free Dataset Distillation for Object Detection

arXiv:2506.01942 · cs.CV · Submitted 2025-06-02 · Read on arXiv

cs.CV

Submitted: 2025-06-02

Updated: 2026-09-23

Code: https://github.com/VILA-Lab/OD3

Terminology

• Distillation — 34× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Ablation study — 8× in this paper · explained in 1 episode
• Core — 7× in this paper · explained in 2 episodes
• Transformer — 7× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Pruning — 3× in this paper · explained in 4 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Clustering — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Active Learning — 1× in this paper · explained in 6 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Fidelity — 1× in this paper · explained in 2 episodes
• Instance Segmentation — 1× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes

Sources

• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Super-Samples from Kernel Herding
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Distilling the Knowledge in a Neural Network
• Focal Loss for Dense Object Detection
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• Dataset Distillation
• Deformable DETR: Deformable Transformers for End-to-End Object Detection

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models