# Reproducibility Study of CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification

Source: [Reproducibility Study of CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification](<https://www.sota2.com/research/paper/68fa73491e209131cea5b8b9>)

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

Data updated: 2025-10-26T02:46:17.278Z

Authors: Manan Shah, Yash Bhalgat

Published: 2024-05-19T14:48:19.000Z

## Abstract

This report is a reproducibility study of the paper "CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification" (Abdelfattah et al, ICCV 2023). Our report makes the following contributions: (1) We provide a reproducible, well commented and open-sourced code implementation for the entire method specified in the original paper. (2) We try to verify the effectiveness of the novel aggregation strategy which uses the CLIP model to initialize the pseudo labels for the subsequent unsupervised multi-label image classification task. (3) We try to verify the effectiveness of the gradient-alignment training method specified in the original paper, which is used to update the network parameters and pseudo labels. The code can be found at https://github.com/cs-mshah/CDUL

## 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/2405.11574>)

[PDF](<https://arxiv.org/pdf/2405.11574.pdf>)