Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning

• URL: http://arxiv.org/abs/2206.08347v1
• Date: Thu, 16 Jun 2022 17:51:19 GMT
• Title: Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning
• Authors: Matthew Gwilliam, Abhinav Shrivastava
• Abstract summary: unsupervised methods for learning image representations have reached impressive results on standard benchmarks. Many methods with substantially different implementations yield results that seem nearly identical on popular benchmarks. We compare methods using performance-based benchmarks such as linear evaluation, nearest neighbor classification, and clustering for several different datasets.
• Score: 37.81297650369799
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: By leveraging contrastive learning, clustering, and other pretext tasks, unsupervised methods for learning image representations have reached impressive results on standard benchmarks. The result has been a crowded field - many methods with substantially different implementations yield results that seem nearly identical on popular benchmarks, such as linear evaluation on ImageNet. However, a single result does not tell the whole story. In this paper, we compare methods using performance-based benchmarks such as linear evaluation, nearest neighbor classification, and clustering for several different datasets, demonstrating the lack of a clear front-runner within the current state-of-the-art. In contrast to prior work that performs only supervised vs. unsupervised comparison, we compare several different unsupervised methods against each other. To enrich this comparison, we analyze embeddings with measurements such as uniformity, tolerance, and centered kernel alignment (CKA), and propose two new metrics of our own: nearest neighbor graph similarity and linear prediction overlap. We reveal through our analysis that in isolation, single popular methods should not be treated as though they represent the field as a whole, and that future work ought to consider how to leverage the complimentary nature of these methods. We also leverage CKA to provide a framework to robustly quantify augmentation invariance, and provide a reminder that certain types of invariance will be undesirable for downstream tasks.

Related papers

• Unsupervised Representation Learning by Balanced Self Attention Matching [2.3020018305241337]
  We present a self-supervised method for embedding image features called BAM. We obtain rich representations and avoid feature collapse by minimizing a loss that matches these distributions to their globally balanced and entropy regularized version. We show competitive performance with leading methods on both semi-supervised and transfer-learning benchmarks.
  arXiv  Detail & Related papers  (2024-08-04T12:52:44Z)
• Asymmetric Patch Sampling for Contrastive Learning [17.922853312470398]
  Asymmetric appearance between positive pair effectively reduces the risk of representation degradation in contrastive learning. We propose a novel asymmetric patch sampling strategy for contrastive learning, to boost the appearance asymmetry for better representations.
  arXiv  Detail & Related papers  (2023-06-05T13:10:48Z)
• Accounting for multiplicity in machine learning benchmark performance [0.0]
  Using the highest-ranked performance as an estimate for state-of-the-art (SOTA) performance is a biased estimator, giving overly optimistic results. In this article, we provide a probability distribution for the case of multiple classifiers so that known analyses methods can be engaged and a better SOTA estimate can be provided.
  arXiv  Detail & Related papers  (2023-03-10T10:32:18Z)
• 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)
• Prototypical Graph Contrastive Learning [141.30842113683775]
  We propose a Prototypical Graph Contrastive Learning (PGCL) approach to mitigate the critical sampling bias issue. Specifically, PGCL models the underlying semantic structure of the graph data via clustering semantically similar graphs into the same group, and simultaneously encourages the clustering consistency for different augmentations of the same graph. For a query, PGCL further reweights its negative samples based on the distance between their prototypes (cluster centroids) and the query prototype.
  arXiv  Detail & Related papers  (2021-06-17T16:45:31Z)
• Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations [78.12377360145078]
  Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. In this paper, we first study how biases in the dataset affect existing methods. We show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets.
  arXiv  Detail & Related papers  (2021-06-10T17:59:13Z)
• With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations [87.72779294717267]
  Using the nearest-neighbor as positive in contrastive losses improves performance significantly on ImageNet classification. We demonstrate empirically that our method is less reliant on complex data augmentations.
  arXiv  Detail & Related papers  (2021-04-29T17:56:08Z)
• Unsupervised Image Segmentation using Mutual Mean-Teaching [12.784209596867495]
  We propose an unsupervised image segmentation model based on the Mutual Mean-Teaching (MMT) framework to produce more stable results. Experimental results demonstrate that the proposed model is able to segment various types of images and achieves better performance than the existing methods.
  arXiv  Detail & Related papers  (2020-12-16T13:13:34Z)
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments [57.33699905852397]
  We propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Our method simultaneously clusters the data while enforcing consistency between cluster assignments. Our method can be trained with large and small batches and can scale to unlimited amounts of data.
  arXiv  Detail & Related papers  (2020-06-17T14:00:42Z)

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.