Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309133673> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4309133673 abstract "Clustering is the task of gathering similar data samples into clusters without using any predefined labels. It has been widely studied in machine learning literature, and recent advancements in deep learning have revived interest in this field. Contrastive clustering (CC) models are a staple of deep clustering in which positive and negative pairs of each data instance are generated through data augmentation. CC models aim to learn a feature space where instance-level and cluster-level representations of positive pairs are grouped together. Despite improving the SOTA, these algorithms ignore the cross-instance patterns, which carry essential information for improving clustering performance. This increases the false-negative-pair rate of the model while decreasing its true-positive-pair rate. In this paper, we propose a novel contrastive clustering method, Cross-instance guided Contrastive Clustering (C3), that considers the cross-sample relationships to increase the number of positive pairs and mitigate the impact of false negative, noise, and anomaly sample on the learned representation of data. In particular, we define a new loss function that identifies similar instances using the instance-level representation and encourages them to aggregate together. Moreover, we propose a novel weighting method to select negative samples in a more efficient way. Extensive experimental evaluations show that our proposed method can outperform state-of-the-art algorithms on benchmark computer vision datasets: we improve the clustering accuracy by 6.6%, 3.3%, 5.0%, 1.3% and 0.3% on CIFAR-10, CIFAR-100, ImageNet-10, ImageNet-Dogs, and Tiny-ImageNet." @default.
- W4309133673 created "2022-11-23" @default.
- W4309133673 creator A5007034199 @default.
- W4309133673 creator A5028642849 @default.
- W4309133673 creator A5073955046 @default.
- W4309133673 date "2022-11-14" @default.
- W4309133673 modified "2023-09-26" @default.
- W4309133673 title "C3: Cross-instance guided Contrastive Clustering" @default.
- W4309133673 doi "https://doi.org/10.48550/arxiv.2211.07136" @default.
- W4309133673 hasPublicationYear "2022" @default.
- W4309133673 type Work @default.
- W4309133673 citedByCount "0" @default.
- W4309133673 crossrefType "posted-content" @default.
- W4309133673 hasAuthorship W4309133673A5007034199 @default.
- W4309133673 hasAuthorship W4309133673A5028642849 @default.
- W4309133673 hasAuthorship W4309133673A5073955046 @default.
- W4309133673 hasBestOaLocation W43091336731 @default.
- W4309133673 hasConcept C119857082 @default.
- W4309133673 hasConcept C124101348 @default.
- W4309133673 hasConcept C126838900 @default.
- W4309133673 hasConcept C13280743 @default.
- W4309133673 hasConcept C138885662 @default.
- W4309133673 hasConcept C153180895 @default.
- W4309133673 hasConcept C154945302 @default.
- W4309133673 hasConcept C17744445 @default.
- W4309133673 hasConcept C183115368 @default.
- W4309133673 hasConcept C185798385 @default.
- W4309133673 hasConcept C199539241 @default.
- W4309133673 hasConcept C202444582 @default.
- W4309133673 hasConcept C205649164 @default.
- W4309133673 hasConcept C2776359362 @default.
- W4309133673 hasConcept C2776401178 @default.
- W4309133673 hasConcept C33923547 @default.
- W4309133673 hasConcept C41008148 @default.
- W4309133673 hasConcept C41895202 @default.
- W4309133673 hasConcept C59404180 @default.
- W4309133673 hasConcept C71924100 @default.
- W4309133673 hasConcept C73555534 @default.
- W4309133673 hasConcept C94625758 @default.
- W4309133673 hasConcept C9652623 @default.
- W4309133673 hasConceptScore W4309133673C119857082 @default.
- W4309133673 hasConceptScore W4309133673C124101348 @default.
- W4309133673 hasConceptScore W4309133673C126838900 @default.
- W4309133673 hasConceptScore W4309133673C13280743 @default.
- W4309133673 hasConceptScore W4309133673C138885662 @default.
- W4309133673 hasConceptScore W4309133673C153180895 @default.
- W4309133673 hasConceptScore W4309133673C154945302 @default.
- W4309133673 hasConceptScore W4309133673C17744445 @default.
- W4309133673 hasConceptScore W4309133673C183115368 @default.
- W4309133673 hasConceptScore W4309133673C185798385 @default.
- W4309133673 hasConceptScore W4309133673C199539241 @default.
- W4309133673 hasConceptScore W4309133673C202444582 @default.
- W4309133673 hasConceptScore W4309133673C205649164 @default.
- W4309133673 hasConceptScore W4309133673C2776359362 @default.
- W4309133673 hasConceptScore W4309133673C2776401178 @default.
- W4309133673 hasConceptScore W4309133673C33923547 @default.
- W4309133673 hasConceptScore W4309133673C41008148 @default.
- W4309133673 hasConceptScore W4309133673C41895202 @default.
- W4309133673 hasConceptScore W4309133673C59404180 @default.
- W4309133673 hasConceptScore W4309133673C71924100 @default.
- W4309133673 hasConceptScore W4309133673C73555534 @default.
- W4309133673 hasConceptScore W4309133673C94625758 @default.
- W4309133673 hasConceptScore W4309133673C9652623 @default.
- W4309133673 hasLocation W43091336731 @default.
- W4309133673 hasOpenAccess W4309133673 @default.
- W4309133673 hasPrimaryLocation W43091336731 @default.
- W4309133673 hasRelatedWork W1544116139 @default.
- W4309133673 hasRelatedWork W2132592511 @default.
- W4309133673 hasRelatedWork W2382607599 @default.
- W4309133673 hasRelatedWork W2383096489 @default.
- W4309133673 hasRelatedWork W2402952899 @default.
- W4309133673 hasRelatedWork W2546942002 @default.
- W4309133673 hasRelatedWork W2874540278 @default.
- W4309133673 hasRelatedWork W2970216048 @default.
- W4309133673 hasRelatedWork W3036234374 @default.
- W4309133673 hasRelatedWork W18669731 @default.
- W4309133673 isParatext "false" @default.
- W4309133673 isRetracted "false" @default.
- W4309133673 workType "article" @default.