# Instance-Level Generation for Representation Learning

Source: [Instance-Level Generation for Representation Learning](<https://www.sota2.com/research/paper/68fa7bff1e209131cea8bc6b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-22T05:00:21.499Z

Authors: Yankun Wu, Zakaria Laskar, Giorgos Kordopatis-Zilos, Noa Garcia, Giorgos Tolias

Published: 2025-10-10T09:14:33.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.09171>)

[PDF](<https://arxiv.org/pdf/2510.09171.pdf>)
