为了使得视觉与学习领域相关从业者快速及时地了解领域的最新发展动态和前沿技术进展,VALSE最新推出了《论文速览》栏目,将在每周发布一至两篇顶会顶刊论文的录制视频,对单个前沿工作进行细致讲解。本期VALSE论文速览选取了来自四川大学和联想研究院的外部引导聚类 (Externally-guided Clustering)的工作。该工作由彭玺教授指导,论文第一作者李云帆博士录制。 论文题目: Image Clustering with External Guidance 作者列表: 李云帆 (四川大学),胡鹏 (四川大学),彭德中 (四川大学),吕建成 (四川大学),范建平 (联想研究院),彭玺 (四川大学) B站观看网址: https://www.bilibili.com/video/BV11NoEYrENd/?share_source=copy_web&vd_source=a70ce9e9822b776de5b16f2ffb335544 复制链接到浏览器打开或点击阅读原文即可跳转至观看页面。 论文摘要: The core of clustering lies in incorporating prior knowledge to construct supervision signals. From classic k-means based on data compactness to recent contrastive clustering guided by self-supervision, the evolution of clustering methods intrinsically corresponds to the progression of supervision signals. At present, substantial efforts have been devoted to mining internal supervision signals from data. Nevertheless, the abundant external knowledge such as semantic descriptions, which naturally conduces to clustering, is regrettably overlooked. In this work, we propose leveraging external knowledge as a new supervision signal to guide clustering. To implement and validate our idea, we design an externally guided clustering method (Text-Aided Clustering, TAC), which leverages the textual semantics of WordNet to facilitate image clustering. Specifically, TAC first selects and retrieves WordNet nouns that best distinguish images to enhance the feature discriminability. Then, TAC collaborates text and image modalities by mutually distilling cross-modal neighborhood information. Experiments demonstrate that TAC achieves state-of-the-art performance on five widely used and three more challenging image clustering benchmarks, including the full ImageNet-1K dataset. 参考文献: [1] Yunfan Li, Peng Hu, Dezhong Peng, Jiancheng Lv, Jianping Fan, Xi Peng. Image Clustering with External Guidance. In Forty-first International Conference on Machine Learning (ICML 2024). 论文链接: https://openreview.net/pdf?id=JSYN891WnB 代码链接: https://github.com/XLearning-SCU/2024-ICML-TAC 视频讲者简介: 李云帆,四川大学计算机学院 2020级直博研究生,导师为彭玺教授,研究方向为深度聚类相关理论、方法和应用,目前已在国际权威刊物Nature Communications/ /IJCV/ICML等上发表论文。 个人主页: https://yunfan-li.github.io/ 特别鸣谢本次论文速览主要组织者: 月度轮值AC:杨帅 (南洋理工大学) |
小黑屋|手机版|Archiver|Vision And Learning SEminar
GMT+8, 2025-10-10 23:19 , Processed in 0.012656 second(s), 14 queries .
Powered by Discuz! X3.4
Copyright © 2001-2020, Tencent Cloud.