Research map / Detection and segmentation / Open-set and few-shot detection

Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation

NeurIPS 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 0 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a collaborative, multi-round generative data augmentation method that uses feedback from the segmentation model to improve sample efficiency of synthetic data for long-tail instance segmentation.

Problem

Long-tail instance segmentation suffers from class imbalance and high annotation costs; prior data synthesis methods select from a pre-generated object pool, leading to inefficient use of generated data.

Approach

A collaborative approach that incorporates feedback from the downstream segmentation model into multi-round generation, so synthetic data is produced iteratively rather than selected from a fixed pre-generated pool.

Closest papers by meaning

• DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data (CVPR 2024 · similarity 0.89)
• A Generative Approach at the Instance-Level for Image Segmentation Under Limited Training Data Conditions (Student Abstract) (AAAI 2025 · similarity 0.89)
• Training-Free Dataset Pruning for Instance Segmentation (ICLR 2025 · similarity 0.88)
• Generative Active Learning for Long-tailed Instance Segmentation (ICML 2024 · similarity 0.86)
• UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation (NeurIPS 2025 · similarity 0.85)
• When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration (ICML 2025 · similarity 0.85)