TY - JOUR
T1 - ProFeat
T2 - Unsupervised image clustering via progressive feature refinement
AU - Kim, Jeonghoon
AU - Im, Sunghoon
AU - Cho, Sunghyun
N1 - Publisher Copyright:
© 2022
PY - 2022/12
Y1 - 2022/12
N2 - Unsupervised image clustering is a chicken-and-egg problem that involves representation learning and clustering. To resolve the inter-dependency between them, many approaches that iteratively perform the two tasks have been proposed, but their accuracy is limited due to inaccurate intermediate representations and clusters. To overcome this, this paper proposes ProFeat, a novel iterative approach to unsupervised image clustering based on progressive feature refinement. To learn discriminative features for clustering while avoiding adversarial influence from inaccurate intermediate clusters, ProFeat rigorously divides representation learning and clustering by modeling a neural network for clustering as a composition of an embedding and a clustering function and introducing an auxiliary embedding function. ProFeat progressively refines representations using confident samples from intermediate clusters using an extended contrastive loss. This paper also proposes ensemble-based feature refinement for more robust clustering. Our experiments demonstrate that ProFeat achieves superior results compared to previous methods.
AB - Unsupervised image clustering is a chicken-and-egg problem that involves representation learning and clustering. To resolve the inter-dependency between them, many approaches that iteratively perform the two tasks have been proposed, but their accuracy is limited due to inaccurate intermediate representations and clusters. To overcome this, this paper proposes ProFeat, a novel iterative approach to unsupervised image clustering based on progressive feature refinement. To learn discriminative features for clustering while avoiding adversarial influence from inaccurate intermediate clusters, ProFeat rigorously divides representation learning and clustering by modeling a neural network for clustering as a composition of an embedding and a clustering function and introducing an auxiliary embedding function. ProFeat progressively refines representations using confident samples from intermediate clusters using an extended contrastive loss. This paper also proposes ensemble-based feature refinement for more robust clustering. Our experiments demonstrate that ProFeat achieves superior results compared to previous methods.
KW - Clustering
KW - Representation learning
KW - Unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85141911331&partnerID=8YFLogxK
U2 - 10.1016/j.patrec.2022.10.029
DO - 10.1016/j.patrec.2022.10.029
M3 - Article
AN - SCOPUS:85141911331
SN - 0167-8655
VL - 164
SP - 166
EP - 172
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
ER -