paper-with-me

Papers

PAWS-VMK: A Unified Approach To Semi-Supervised Learning And Out-of-Distribution Detection

2023-11-28 · Evelyn Mannix, Howard Bondell

This paper describes PAWS-VMK, a prototypical deep learning approach that obtains state-of-the-art results for image classification tasks in both a semi-supervised learning (SSL) and out-of-distribution (OOD) detection context. We consider developments in the fields of SSL, OOD detection, and computer vision foundation models to introduce a number of innovations that connect the key ideas within these works to create PAWS-VMK. These innovations include (1) parametric von Mises-Fisher Stochastic Neighbour Embedding (vMF-SNE) to initialise a projection head for SSL using the high-quality embeddings of the foundation model; (2) the PAWS-MixMatch loss, that creates more compact embeddings and obtains higher accuracy in comparison to the consistency loss used in PAWS and (3) simple $k$-Means prototype selection (SKMPS), a simple technique that obtains competitive performance with more complex unsupervised label selection approaches. PAWS-VMK sets new benchmarks in semi-supervised learning for CIFAR-10 (99.2%) and CIFAR-100 (89.8%) with four labelled instances per class, and Food-101 (90.1%) with two labelled instances per class. We also observe that PAWS-VMK can efficiently detect OOD samples in a manner that is competitive with specialised methods specifically designed for this purpose, achieving 93.1/98.0 and 95.2/96.3 on the CIFAR-10 and CIFAR-100 OpenOOD benchmarks.

📄 PDF Abstract BibTeX arXiv:2311.17093

Code (0)

등록된 구현이 없습니다.

Tasks

Benchmarkingimage-classificationImage ClassificationOut-of-Distribution DetectionOut of Distribution (OOD) DetectionPrototype Selection

Similar Papers 제목 키워드 기반

RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data

2023-02-28 · Sangwoo Mo, Jong-Chyi Su, Chih-Yao Ma, Mido Assran 외

Semi-supervised learning aims to train a model using limited labels. State-of-the-art semi-supervised methods for image classification such as PAWS rely on self-supervised representations learned with large-scale unlabel…

Density Estimationimage-classificationImage ClassificationRepresentation Learning

Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

2021-04-28 · ICCV 2021 10 · Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski 외

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabele…

Image ClassificationPseudo LabelSemi-Supervised Image Classification

RuPAWS: A Russian Adversarial Dataset for Paraphrase Identification

2022-06-01 · LREC 2022 6 · Nikita Martynov, Irina Krotova, Varvara Logacheva, Alexander Panchenko 외

Paraphrase identification task can be easily challenged by changing word order, e.g. as in “Can a good person become bad?”. While for English this problem was tackled by the PAWS dataset (Zhang et al., 2019), datasets fo…

Paraphrase Identification

Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning

2023-05-17 · Evelyn J. Mannix, Howard D. Bondell

In many machine learning applications, labeling datasets can be an arduous and time-consuming task. Although research has shown that semi-supervised learning techniques can achieve high accuracy with very few labels with…

Self-Supervised Learning

Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning

2021-12-08 · KL Navaneet, Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Kossar Pourahmadi 외

We are interested in representation learning in self-supervised, supervised, and semi-supervised settings. Some recent self-supervised learning methods like mean-shift (MSF) cluster images by pulling the embedding of a q…

Pseudo LabelRepresentation LearningSelf-Supervised Learning