Meta Discovery: Learning to Discover Novel Classes given Very Limited Data

• URL: http://arxiv.org/abs/2102.04002v1
• Date: Mon, 8 Feb 2021 04:53:14 GMT
• Title: Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
• Authors: Haoang Chi and Feng Liu and Wenjing Yang and Long Lan and Tongliang Liu and Gang Niu and Bo Han
• Abstract summary: In this paper, we analyze and improve L2DNC by linking it to meta-learning. L2DNC is not only theoretically solvable, but also can be empirically solved by meta-learning algorithms slightly modified to fit our proposed framework.
• Score: 59.90813997957849
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In learning to discover novel classes(L2DNC), we are given labeled data from seen classes and unlabeled data from unseen classes, and we need to train clustering models for the unseen classes. Since L2DNC is a new problem, its application scenario and implicit assumption are unclear. In this paper, we analyze and improve it by linking it to meta-learning: although there are no meta-training and meta-test phases, the underlying assumption is exactly the same, namely high-level semantic features are shared among the seen and unseen classes. Under this assumption, L2DNC is not only theoretically solvable, but also can be empirically solved by meta-learning algorithms slightly modified to fit our proposed framework. This L2DNC methodology significantly reduces the amount of unlabeled data needed for training and makes it more practical, as demonstrated in experiments. The use of very limited data is also justified by the application scenario of L2DNC: since it is unnatural to label only seen-class data, L2DNC is causally sampling instead of labeling. The unseen-class data should be collected on the way of collecting seen-class data, which is why they are novel and first need to be clustered.

Related papers

• MetaGCD: Learning to Continually Learn in Generalized Category Discovery [26.732455383707798]
  We consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data. The goal is to continually discover novel classes while maintaining the performance in known classes. We propose an approach, called MetaGCD, to learn how to incrementally discover with less forgetting.
  arXiv  Detail & Related papers  (2023-08-21T22:16:49Z)
• CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels [14.285609493077965]
  Clustering-enhanced Linear Discriminative Analysis, a novel approach that improves the text classification accuracy with a very weak-supervision signal. Our framework draws a precise decision boundary without accessing weights or gradients of the LM model or data labels.
  arXiv  Detail & Related papers  (2023-06-05T08:35:31Z)
• Detecting Novelties with Empty Classes [6.953730499849023]
  We build upon anomaly detection to retrieve out-of-distribution (OoD) data as candidates for new classes. We introduce two loss functions, which 1) entice the DNN to assign OoD samples to the empty classes and 2) to minimize the inner-class feature distances between them.
  arXiv  Detail & Related papers  (2023-04-30T19:52:47Z)
• Universal Semi-Supervised Learning for Medical Image Classification [21.781201758182135]
  Semi-supervised learning (SSL) has attracted much attention since it reduces the expensive costs of collecting adequate well-labeled training data. Traditional SSL is built upon an assumption that labeled and unlabeled data should be from the same distribution. We propose a unified framework to leverage unseen unlabeled data for open-scenario semi-supervised medical image classification.
  arXiv  Detail & Related papers  (2023-04-08T16:12:36Z)
• Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning [69.81438976273866]
  Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and test data contain new categories (outliers) not observed in labeled data (inliers) We introduce evidential deep learning (EDL) as an outlier detector to quantify different types of uncertainty, and design different uncertainty metrics for self-training and inference. We propose a novel adaptive negative optimization strategy, making EDL more tailored to the unlabeled dataset containing both inliers and outliers.
  arXiv  Detail & Related papers  (2023-03-21T09:07:15Z)
• Are labels informative in semi-supervised learning? -- Estimating and leveraging the missing-data mechanism [4.675583319625962]
  Semi-supervised learning is a powerful technique for leveraging unlabeled data to improve machine learning models. It can be affected by the presence of informative'' labels, which occur when some classes are more likely to be labeled than others. We propose a novel approach to address this issue by estimating the missing-data mechanism and using inverse propensity weighting to debias any SSL algorithm.
  arXiv  Detail & Related papers  (2023-02-15T09:18:46Z)
• Few-Shot Non-Parametric Learning with Deep Latent Variable Model [50.746273235463754]
  We propose Non-Parametric learning by Compression with Latent Variables (NPC-LV) NPC-LV is a learning framework for any dataset with abundant unlabeled data but very few labeled ones. We show that NPC-LV outperforms supervised methods on all three datasets on image classification in low data regime.
  arXiv  Detail & Related papers  (2022-06-23T09:35:03Z)
• L2B: Learning to Bootstrap Robust Models for Combating Label Noise [52.02335367411447]
  This paper introduces a simple and effective method, named Learning to Bootstrap (L2B) It enables models to bootstrap themselves using their own predictions without being adversely affected by erroneous pseudo-labels. It achieves this by dynamically adjusting the importance weight between real observed and generated labels, as well as between different samples through meta-learning.
  arXiv  Detail & Related papers  (2022-02-09T05:57:08Z)
• Improving Calibration for Long-Tailed Recognition [68.32848696795519]
  We propose two methods to improve calibration and performance in such scenarios. For dataset bias due to different samplers, we propose shifted batch normalization. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-01T13:55:21Z)
• Learning Adaptive Embedding Considering Incremental Class [55.21855842960139]
  Class-Incremental Learning (CIL) aims to train a reliable model with the streaming data, which emerges unknown classes sequentially. Different from traditional closed set learning, CIL has two main challenges: 1) Novel class detection. After the novel classes are detected, the model needs to be updated without re-training using entire previous data.
  arXiv  Detail & Related papers  (2020-08-31T04:11:24Z)

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.