ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision

• URL: http://arxiv.org/abs/2304.09369v1
• Date: Wed, 19 Apr 2023 01:51:08 GMT
• Title: ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision
• Authors: Seongho Joe, Byoungjip Kim, Hoyoung Kang, Kyoungwon Park, Bogun Kim, Jaeseon Park, Joonseok Lee, Youngjune Gwon
• Abstract summary: We propose ContraCluster, an unsupervised image classification method that combines clustering with the power of contrastive self-supervised learning. ContraCluster consists of three stages: (1) contrastive self-supervised pre-training (CPT), (2) contrastive prototype sampling (CPS), and (3) prototype-based semi-supervised fine-tuning (PB-SFT). We demonstrate empirically that ContraCluster achieves new state-of-the-art results for standard benchmark datasets including CIFAR-10, STL-10, and ImageNet-10.
• Score: 7.819942809508631
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification method that combines clustering with the power of contrastive self-supervised learning. ContraCluster consists of three stages: (1) contrastive self-supervised pre-training (CPT), (2) contrastive prototype sampling (CPS), and (3) prototype-based semi-supervised fine-tuning (PB-SFT). CPS can select highly accurate, categorically prototypical images in an embedding space learned by contrastive learning. We use sampled prototypes as noisy labeled data to perform semi-supervised fine-tuning (PB-SFT), leveraging small prototypes and large unlabeled data to further enhance the accuracy. We demonstrate empirically that ContraCluster achieves new state-of-the-art results for standard benchmark datasets including CIFAR-10, STL-10, and ImageNet-10. For example, ContraCluster achieves about 90.8% accuracy for CIFAR-10, which outperforms DAC (52.2%), IIC (61.7%), and SCAN (87.6%) by a large margin. Without any labels, ContraCluster can achieve a 90.8% accuracy that is comparable to 95.8% by the best supervised counterpart.

Related papers

• 3C: Confidence-Guided Clustering and Contrastive Learning for Unsupervised Person Re-Identification [10.173539278449262]
  Unsupervised person re-identification (Re-ID) aims to learn a feature network with cross-camera retrieval capability in unlabelled datasets. A confidence-guided clustering and contrastive learning (3C) framework is proposed for unsupervised person Re-ID.
  arXiv  Detail & Related papers  (2024-08-18T13:14:20Z)
• Rethinking cluster-conditioned diffusion models for label-free image synthesis [1.4624458429745086]
  Diffusion-based image generation models can enhance image quality when conditioned on ground truth labels. We investigate how individual clustering determinants, such as the number of clusters and the clustering method, impact image synthesis.
  arXiv  Detail & Related papers  (2024-03-01T14:47:46Z)
• C3: Cross-instance guided Contrastive Clustering [8.953252452851862]
  Clustering is the task of gathering similar data samples into clusters without using any predefined labels. We propose a novel contrastive clustering method, Cross-instance guided Contrastive Clustering (C3) Our proposed method can outperform state-of-the-art algorithms on benchmark computer vision datasets.
  arXiv  Detail & Related papers  (2022-11-14T06:28:07Z)
• Masked Unsupervised Self-training for Zero-shot Image Classification [98.23094305347709]
  Masked Unsupervised Self-Training (MUST) is a new approach which leverages two different and complimentary sources of supervision: pseudo-labels and raw images. MUST improves upon CLIP by a large margin and narrows the performance gap between unsupervised and supervised classification.
  arXiv  Detail & Related papers  (2022-06-07T02:03:06Z)
• Generalized Supervised Contrastive Learning [3.499054375230853]
  We introduce a generalized supervised contrastive loss, which measures cross-entropy between label similarity and latent similarity. Compared to existing contrastive learning frameworks, we construct a tailored framework: the Generalized Supervised Contrastive Learning (GenSCL) GenSCL achieves a top-1 accuracy of 77.3% on ImageNet, a 4.1% improvement over traditional supervised contrastive learning.
  arXiv  Detail & Related papers  (2022-06-01T10:38:21Z)
• Weakly Supervised Contrastive Learning [68.47096022526927]
  We introduce a weakly supervised contrastive learning framework (WCL) to tackle this issue. WCL achieves 65% and 72% ImageNet Top-1 Accuracy using ResNet50, which is even higher than SimCLRv2 with ResNet101.
  arXiv  Detail & Related papers  (2021-10-10T12:03:52Z)
• To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection [95.21700830273221]
  Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions. We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
  arXiv  Detail & Related papers  (2021-09-04T02:45:22Z)
• Neighborhood Contrastive Learning for Novel Class Discovery [79.14767688903028]
  We build a new framework, named Neighborhood Contrastive Learning, to learn discriminative representations that are important to clustering performance. We experimentally demonstrate that these two ingredients significantly contribute to clustering performance and lead our model to outperform state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2021-06-20T17:34:55Z)
• Semi-supervised Contrastive Learning with Similarity Co-calibration [72.38187308270135]
  We propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL) SsCL combines the well-known contrastive loss in self-supervised learning with the cross entropy loss in semi-supervised learning. We show that SsCL produces more discriminative representation and is beneficial to few shot learning.
  arXiv  Detail & Related papers  (2021-05-16T09:13:56Z)
• Contrastive Clustering [57.71729650297379]
  We propose Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. In particular, CC achieves an NMI of 0.705 (0.431) on the CIFAR-10 (CIFAR-100) dataset, which is an up to 19% (39%) performance improvement compared with the best baseline.
  arXiv  Detail & Related papers  (2020-09-21T08:54:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.