# Fine-Grained Representation Learning via Multi-Level Contrastive Learning without Class Priors

Source: [Fine-Grained Representation Learning via Multi-Level Contrastive Learning without Class Priors](<https://www.sota2.com/research/paper/68fa74e81e209131cea64a1c>)

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

Data updated: 2025-10-26T03:21:26.418Z

Authors: Houwang Jiang, Zhuxian Liu, Guodong Liu, Xiaolong Liu, Shihua Zhan

Published: 2024-09-07T16:39:14.000Z

## Abstract

Recent advances in unsupervised representation learning often rely on knowing the number of classes to improve feature extraction and clustering. However, this assumption raises an important question: is the number of classes always necessary, and do class labels fully capture the fine-grained features within the data? In this paper, we propose Contrastive Disentangling (CD), a framework designed to learn representations without relying on class priors. CD leverages a multi-level contrastive learning strategy, integrating instance-level and feature-level contrastive losses with a normalized entropy loss to capture semantically rich and fine-grained representations. Specifically, (1) the instance-level contrastive loss separates feature representations across samples; (2) the feature-level contrastive loss promotes independence among feature heads; and (3) the normalized entropy loss ensures feature diversity and prevents feature collapse. Extensive experiments on CIFAR-10, CIFAR-100, STL-10, and ImageNet-10 demonstrate that CD outperforms existing methods in scenarios where class information is unavailable or ambiguous. The code is available at https://github.com/Hoper-J/Contrastive-Disentangling.

## 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/2409.04867>)

[PDF](<https://arxiv.org/pdf/2409.04867.pdf>)
