2025/10/10 by Yankun Wu, Zakaria Laskar, Wu, Yankun +8
Computer Science · #Advanced Image and Video Retrieval Techniques #Domain Adaptation and Few-Shot Learning #External Data Representation #Feature learning #Generative Adversarial Networks and Image Synthesis #Granularity #Limiting #Object (grammar) #Range (aeronautics) #Representation (politics) #Training set #cs.CV
paper · pdf · doi:10.48550/arxiv.2510.09171
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/10/10 · openalex created_date 2025/10/14 · openalex updated_date 2026/08/05
Instance-level recognition (ILR) focuses on identifying individual objects rather than broad categories, offering the highest granularity in image classification. However, this fine-grained nature makes creating large-scale annotated datasets challenging, limiting ILR's real-world applicability across domains. To overcome this, we introduce a novel approach that synthetically generates diverse object instances from multiple domains under varied conditions and backgrounds, forming a large-scale training set. Unlike prior work on automatic data synthesis, our method is the first to address ILR-specific challenges without relying on any real images. Fine-tuning foundation vision models on the generated data significantly improves retrieval performance across seven ILR benchmarks spanning multiple domains. Our approach offers a new, efficient, and effective alternative to extensive data collection and curation, introducing a new ILR paradigm where the only input is the names of the target domains, unlocking a wide range of real-world applications. The code and pretrained models are publicly available at https://github.com/yankungou/ILGen.