Deep Clustering by Semantic Contrastive Learning

03/03/2021
by   Jiabo Huang, et al.
0

Whilst contrastive learning has achieved remarkable success in self-supervised representation learning, its potential for deep clustering remains unknown. This is due to its fundamental limitation that the instance discrimination strategy it takes is not class sensitive and hence unable to reason about the underlying decision boundaries between semantic concepts or classes. In this work, we solve this problem by introducing a novel variant called Semantic Contrastive Learning (SCL). It explores the characteristics of both conventional contrastive learning and deep clustering by imposing distance-based cluster structures on unlabelled training data and also introducing a discriminative contrastive loss formulation. For explicitly modelling class boundaries on-the-fly, we further formulate a clustering consistency condition on the two different predictions given by visual similarities and semantic decision boundaries. By advancing implicit representation learning towards explicit understandings of visual semantics, SCL can amplify jointly the strengths of contrastive learning and deep clustering in a unified approach. Extensive experiments show that the proposed model outperforms the state-of-the-art deep clustering methods on six challenging object recognition benchmarks, especially on finer-grained and larger datasets.

READ FULL TEXT
research
12/31/2021

Representation Learning via Consistent Assignment of Views to Clusters

We introduce Consistent Assignment for Representation Learning (CARL), a...
research
09/26/2021

Cluster Analysis with Deep Embeddings and Contrastive Learning

Unsupervised disentangled representation learning is a long-standing pro...
research
09/16/2021

Dense Semantic Contrast for Self-Supervised Visual Representation Learning

Self-supervised representation learning for visual pre-training has achi...
research
11/23/2021

Exploring Non-Contrastive Representation Learning for Deep Clustering

Existing deep clustering methods rely on contrastive learning for repres...
research
08/07/2020

Deep Robust Clustering by Contrastive Learning

Recently, many unsupervised deep learning methods have been proposed to ...
research
03/24/2021

Supporting Clustering with Contrastive Learning

Unsupervised clustering aims at discovering the semantic categories of d...
research
04/26/2022

Robust Audio-Visual Instance Discrimination via Active Contrastive Set Mining

The recent success of audio-visual representation learning can be largel...

Please sign up or login with your details

Forgot password? Click here to reset