Open AccessPosted Content
Clustering based Contrastive Learning for Improving Face Representations
TL;DR: This work presents Clustering-based Contrastive Learning (CCL), a new clustering- based representation learning approach that uses labels obtained from clustering along with video constraints to learn discriminative face features.
read more
Abstract: A good clustering algorithm can discover natural groupings in data. These groupings, if used wisely, provide a form of weak supervision for learning representations. In this work, we present Clustering-based Contrastive Learning (CCL), a new clustering-based representation learning approach that uses labels obtained from clustering along with video constraints to learn discriminative face features. We demonstrate our method on the challenging task of learning representations for video face clustering. Through several ablation studies, we analyze the impact of creating pair-wise positive and negative labels from different sources. Experiments on three challenging video face clustering datasets: BBT-0101, BF-0502, and ACCIO show that CCL achieves a new state-of-the-art on all datasets.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Posted Content
Contrastive Clustering
TL;DR: A one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning, which remarkably outperforms 17 competitive clustering methods on six challenging image benchmarks.
658
Large Scale Holistic Video Understanding
Ali Diba,Mohsen Fayyaz,Vivek Sharma,Manohar Paluri,Jürgen Gall,Rainer Stiefelhagen,Luc Van Gool,Luc Van Gool +7 more
- 23 Aug 2020
TL;DR: A new spatio-temporal deep neural network architecture called "Holistic Appearance and Temporal Network"~(HATNet) that builds on fusing 2D and 3D architectures into one by combining intermediate representations of appearance and temporal cues is introduced.
TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
TL;DR: This work aims to activate LLM's ability for TS data by designing a TS embedding method suitable for LLM, named TEST, and shows that the pre-trained LLM with TEST strategy can achieve better or comparable performance than today's SOTA TS models and offer benefits for few-shot and generalization.
49
Graph Contrastive Partial Multi-View Clustering
TL;DR: In this article , an augmentation-free graph contrastive learning framework is proposed to solve the problem of partial multi-view clustering, where the representations of similar samples (i.e., belonging to the same cluster) should be similar.
32
ClusterSCL: Cluster-Aware Supervised Contrastive Learning on Graphs
Yanling Wang,Ping Zhang,Haoyang Li,Yuxiao Dong,Hongzhi Yin,Cuiping Li,Hong Chen,Hongzhi,Yin +8 more
- 25 Apr 2022
TL;DR: ClusterSCL introduces the strategy of cluster-aware data augmentation and integrates it with the SupCon loss for graph learning tasks and demonstrates the superiority of ClusterSCL over the cross-entropy, SupCon, and other graph contrastive objectives.
20
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
•Posted Content
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
81.7K
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Jacob Devlin,Ming-Wei Chang,Kenton Lee,Kristina Toutanova +3 more
- 11 Oct 2018
TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
24.6K
•Proceedings Article
Distributed Representations of Words and Phrases and their Compositionality
Tomas Mikolov,Ilya Sutskever,Kai Chen,Greg S. Corrado,Jeffrey Dean +4 more
- 05 Dec 2013
TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.