Supervised Stochastic Neighbor Embedding Using Contrastive Learning

• URL: http://arxiv.org/abs/2309.08077v1
• Date: Fri, 15 Sep 2023 00:26:21 GMT
• Title: Supervised Stochastic Neighbor Embedding Using Contrastive Learning
• Authors: Yi Zhang
• Abstract summary: Clusters of samples belonging to the same class are pulled together in low-dimensional embedding space. We extend the self-supervised contrastive approach to the fully-supervised setting, allowing us to effectively leverage label information.
• Score: 4.560284382063488
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Stochastic neighbor embedding (SNE) methods $t$-SNE, UMAP are two most popular dimensionality reduction methods for data visualization. Contrastive learning, especially self-supervised contrastive learning (SSCL), has showed great success in embedding features from unlabeled data. The conceptual connection between SNE and SSCL has been exploited. In this work, within the scope of preserving neighboring information of a dataset, we extend the self-supervised contrastive approach to the fully-supervised setting, allowing us to effectively leverage label information. Clusters of samples belonging to the same class are pulled together in low-dimensional embedding space, while simultaneously pushing apart clusters of samples from different classes.

Related papers

• Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection [75.02249869573994]
  In open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes. Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes. We propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector)
  arXiv  Detail & Related papers  (2024-11-20T02:57:35Z)
• Linking data separation, visual separation, and classifier performance using pseudo-labeling by contrastive learning [125.99533416395765]
  We argue that the performance of the final classifier depends on the data separation present in the latent space and visual separation present in the projection. We demonstrate our results by the classification of five real-world challenging image datasets of human intestinal parasites with only 1% supervised samples.
  arXiv  Detail & Related papers  (2023-02-06T10:01:38Z)
• Hyperspherical Consistency Regularization [45.00073340936437]
  We explore the relationship between self-supervised learning and supervised learning, and study how self-supervised learning helps robust data-efficient deep learning. We propose hyperspherical consistency regularization (HCR), a simple yet effective plug-and-play method, to regularize the classifier using feature-dependent information and thus avoid bias from labels.
  arXiv  Detail & Related papers  (2022-06-02T02:41:13Z)
• Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding [12.421540007814937]
  Self-supervised contrastive learning (SSCL) has achieved great success in extracting powerful features from unlabeled data. We contribute to the theoretical understanding of SSCL and uncover its connection to the classic data visualization method, neighbor embedding. We provide novel analysis on domain-agnostic augmentations, implicit bias and robustness of learned features.
  arXiv  Detail & Related papers  (2022-05-30T02:39:29Z)
• Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution [77.85461690214551]
  Learning from fully-unlabeled data is challenging in Multimedia Forensics problems, such as Person Re-Identification and Text Authorship Attribution. Recent self-supervised learning methods have shown to be effective when dealing with fully-unlabeled data in cases where the underlying classes have significant semantic differences. We propose a strategy to tackle Person Re-Identification and Text Authorship Attribution by enabling learning from unlabeled data even when samples from different classes are not prominently diverse.
  arXiv  Detail & Related papers  (2022-02-07T13:08:11Z)
• Cluster Analysis with Deep Embeddings and Contrastive Learning [0.0]
  This work proposes a novel framework for performing image clustering from deep embeddings. Our approach jointly learns representations and predicts cluster centers in an end-to-end manner. Our framework performs on par with widely accepted clustering methods and outperforms the state-of-the-art contrastive learning method on the CIFAR-10 dataset.
  arXiv  Detail & Related papers  (2021-09-26T22:18:15Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)
• Stochastic Cluster Embedding [14.485496311015398]
  Neighbor Embedding (NE) aims to preserve pairwise similarities between data items. NE methods such as Neighbor Embedding (SNE) may leave large-scale patterns such as clusters hidden. We propose a new cluster visualization method based on Neighbor Embedding.
  arXiv  Detail & Related papers  (2021-08-18T07:07:28Z)
• Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning [101.28281124670647]
  Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. We propose a novel training mechanism that could effectively exploit the presence of OOD data for enhanced feature learning. Our approach substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2021-08-12T09:14:44Z)
• ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning [52.831894583501395]
  Continual learning assumes the incoming data are fully labeled, which might not be applicable in real applications. We propose deep Online Replay with Discriminator Consistency (ORDisCo) to interdependently learn a classifier with a conditional generative adversarial network (GAN) We show ORDisCo achieves significant performance improvement on various semi-supervised learning benchmark datasets for SSCL.
  arXiv  Detail & Related papers  (2021-01-02T09:04:14Z)

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.