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

2024/05/19 by Manan Shah, Shah, Manan, Yash Bhalgat +1
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Text and Document Classification Technologies

paper · pdf · doi:10.48550/arxiv.2405.11574

openalex publication_date 2024/05/19 · openalex created_date 2024/05/22 · openalex updated_date 2026/07/28

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

Related

• CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification
• Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification
• Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning
• Improving CLIP Robustness with Knowledge Distillation and Self-Training
• Multi-Label Self-Supervised Learning with Scene Images