Transductive Few-Shot Learning: Clustering is All You Need?

• URL: http://arxiv.org/abs/2106.09516v1
• Date: Wed, 16 Jun 2021 16:14:01 GMT
• Title: Transductive Few-Shot Learning: Clustering is All You Need?
• Authors: Imtiaz Masud Ziko, Malik Boudiaf, Jose Dolz, Eric Granger and Ismail Ben Ayed
• Abstract summary: We investigate a general formulation for transive few-shot learning, which integrates prototype-based objectives. We find that our method yields competitive performances, in term of accuracy and optimization, while scaling up to large problems. Surprisingly, we find that our general model already achieve competitive performances in comparison to the state-of-the-art learning.
• Score: 31.21306826132773
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate a general formulation for clustering and transductive few-shot learning, which integrates prototype-based objectives, Laplacian regularization and supervision constraints from a few labeled data points. We propose a concave-convex relaxation of the problem, and derive a computationally efficient block-coordinate bound optimizer, with convergence guarantee. At each iteration,our optimizer computes independent (parallel) updates for each point-to-cluster assignment. Therefore, it could be trivially distributed for large-scale clustering and few-shot tasks. Furthermore, we provides a thorough convergence analysis based on point-to-set maps. Were port comprehensive clustering and few-shot learning experiments over various data sets, showing that our method yields competitive performances, in term of accuracy and optimization quality, while scaling up to large problems. Using standard training on the base classes, without resorting to complex meta-learning and episodic-training strategies, our approach outperforms state-of-the-art few-shot methods by significant margins, across various models, settings and data sets. Surprisingly, we found that even standard clustering procedures (e.g., K-means), which correspond to particular, non-regularized cases of our general model, already achieve competitive performances in comparison to the state-of-the-art in few-shot learning. These surprising results point to the limitations of the current few-shot benchmarks, and question the viability of a large body of convoluted few-shot learning techniques in the recent literature.

Related papers

• Self-Supervised Graph Embedding Clustering [70.36328717683297]
  K-means one-step dimensionality reduction clustering method has made some progress in addressing the curse of dimensionality in clustering tasks. We propose a unified framework that integrates manifold learning with K-means, resulting in the self-supervised graph embedding framework.
  arXiv  Detail & Related papers  (2024-09-24T08:59:51Z)
• Stable Cluster Discrimination for Deep Clustering [7.175082696240088]
  Deep clustering can optimize representations of instances (i.e., representation learning) and explore the inherent data distribution. The coupled objective implies a trivial solution that all instances collapse to the uniform features. In this work, we first show that the prevalent discrimination task in supervised learning is unstable for one-stage clustering. A novel stable cluster discrimination (SeCu) task is proposed and a new hardness-aware clustering criterion can be obtained accordingly.
  arXiv  Detail & Related papers  (2023-11-24T06:43:26Z)
• Large-scale Fully-Unsupervised Re-Identification [78.47108158030213]
  We propose two strategies to learn from large-scale unlabeled data. The first strategy performs a local neighborhood sampling to reduce the dataset size in each without violating neighborhood relationships. A second strategy leverages a novel Re-Ranking technique, which has a lower time upper bound complexity and reduces the memory complexity from O(n2) to O(kn) with k n.
  arXiv  Detail & Related papers  (2023-07-26T16:19:19Z)
• Neural Capacitated Clustering [6.155158115218501]
  We propose a new method for the Capacitated Clustering Problem (CCP) that learns a neural network to predict the assignment probabilities of points to cluster centers. In our experiments on artificial data and two real world datasets our approach outperforms several state-of-the-art mathematical and solvers from the literature.
  arXiv  Detail & Related papers  (2023-02-10T09:33:44Z)
• Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning [146.11600461034746]
  Method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. We prove that the core reason for this is lack of a clustering-friendly property in the embedding space.
  arXiv  Detail & Related papers  (2022-09-27T19:04:36Z)
• Adaptively-weighted Integral Space for Fast Multiview Clustering [54.177846260063966]
  We propose an Adaptively-weighted Integral Space for Fast Multiview Clustering (AIMC) with nearly linear complexity. Specifically, view generation models are designed to reconstruct the view observations from the latent integral space. Experiments conducted on several realworld datasets confirm the superiority of the proposed AIMC method.
  arXiv  Detail & Related papers  (2022-08-25T05:47:39Z)
• 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)
• Fast and Interpretable Consensus Clustering via Minipatch Learning [0.0]
  We develop IMPACC: Interpretable MiniPatch Adaptive Consensus Clustering. We develop adaptive sampling schemes for observations, which result in both improved reliability and computational savings. Results show that our approach yields more accurate and interpretable cluster solutions.
  arXiv  Detail & Related papers  (2021-10-05T22:39:28Z)
• You Never Cluster Alone [150.94921340034688]
  We extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation. We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one. By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps.
  arXiv  Detail & Related papers  (2021-06-03T14:59:59Z)
• Fairness, Semi-Supervised Learning, and More: A General Framework for Clustering with Stochastic Pairwise Constraints [32.19047459493177]
  We introduce a novel family of emphstochastic pairwise constraints, which we incorporate into several essential clustering objectives. We show that these constraints can succinctly model an intriguing collection of applications, including emphIndividual Fairness in clustering and emphMust-link constraints in semi-supervised learning.
  arXiv  Detail & Related papers  (2021-03-02T20:27:58Z)
• Simple and Scalable Sparse k-means Clustering via Feature Ranking [14.839931533868176]
  We propose a novel framework for sparse k-means clustering that is intuitive, simple to implement, and competitive with state-of-the-art algorithms. Our core method readily generalizes to several task-specific algorithms such as clustering on subsets of attributes and in partially observed data settings.
  arXiv  Detail & Related papers  (2020-02-20T02:41:02Z)

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.