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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shah, Manan, Bhalgat, Yash
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914802544148480
author Shah, Manan
Bhalgat, Yash
author_facet Shah, Manan
Bhalgat, Yash
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2405_11574
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reproducibility Study of CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification
Shah, Manan
Bhalgat, Yash
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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
title Reproducibility Study of CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.11574