OD3: Optimization-free Dataset Distillation for Object Detection

arXiv:2506.01942v2 Announce Type: replace Abstract: Training large neural networks on large-scale datasets requires substantial computational resources, particularly for dense prediction tasks such as object detection. Although dataset distillation (DD) has been proposed to alleviate these demands by synthesizing compact datasets from larger ones, most existing work focuses solely on image classification, leaving the more complex detection setting largely unexplored. In this paper, we introduce OD3, a novel optimization-free data distillation framework specifically designed for object detection. Our approach involves two stages: first, a candidate selection process in which object instances are iteratively placed in synthesized images based on their suitable locations, and second, a candidate screening process using a pre-trained observer model to remove low-confidence objects. We perform our data synthesis framework on MS COCO and PASCAL VOC, two popular detection datasets, with compression ratios ranging from 0.25% to 5%. Compared to the prior solely existing dataset distillation method on detection and conventional core set selection methods, OD3 delivers superior accuracy, establishes new state-of-the-art results, surpassing prior best method by more than 14% on COCO mAP50 at a compression ratio of 1.0%. Code is available at: https://github.com/VILA-Lab/OD3.

Related

• Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders
• StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets
• A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction
• Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
• Domain-Specialized Object Detection via Model-Level Mixtures of Experts

Source: arXiv cs.CV | 2026-04-21