MIX'EM: Unsupervised Image Classification using a Mixture of Embeddings

• URL: http://arxiv.org/abs/2007.09502v2
• Date: Fri, 2 Oct 2020 23:01:29 GMT
• Title: MIX'EM: Unsupervised Image Classification using a Mixture of Embeddings
• Authors: Ali Varamesh, Tinne Tuytelaars
• Abstract summary: We present MIX'EM, a novel solution for unsupervised image classification. We conduct extensive experiments and analyses on STL10, CIFAR10, and CIFAR100-20 datasets. We achieve state-of-the-art classification accuracy of 78%, 82%, and 44%, respectively.
• Score: 44.29313588655997
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present MIX'EM, a novel solution for unsupervised image classification. MIX'EM generates representations that by themselves are sufficient to drive a general-purpose clustering algorithm to deliver high-quality classification. This is accomplished by building a mixture of embeddings module into a contrastive visual representation learning framework in order to disentangle representations at the category level. It first generates a set of embedding and mixing coefficients from a given visual representation, and then combines them into a single embedding. We introduce three techniques to successfully train MIX'EM and avoid degenerate solutions; (i) diversify mixture components by maximizing entropy, (ii) minimize instance conditioned component entropy to enforce a clustered embedding space, and (iii) use an associative embedding loss to enforce semantic separability. By applying (i) and (ii), semantic categories emerge through the mixture coefficients, making it possible to apply (iii). Subsequently, we run K-means on the representations to acquire semantic classification. We conduct extensive experiments and analyses on STL10, CIFAR10, and CIFAR100-20 datasets, achieving state-of-the-art classification accuracy of 78\%, 82\%, and 44\%, respectively. To achieve robust and high accuracy, it is essential to use the mixture components to initialize K-means. Finally, we report competitive baselines (70\% on STL10) obtained by applying K-means to the "normalized" representations learned using the contrastive loss.

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)
• A consensus-constrained parsimonious Gaussian mixture model for clustering hyperspectral images [0.0]
  Food engineers use hyperspectral images to classify the type and quality of a food sample. In order to train these methods, every pixel in each training image needs to be labelled. A consensus-constrained parsimonious Gaussian mixture model (ccPGMM) is proposed to label pixels in hyperspectral images.
  arXiv  Detail & Related papers  (2024-03-05T22:23:43Z)
• Fast Semisupervised Unmixing Using Nonconvex Optimization [80.11512905623417]
  We introduce a novel convex convex model for semi/library-based unmixing. We demonstrate the efficacy of Alternating Methods of sparse unsupervised unmixing.
  arXiv  Detail & Related papers  (2024-01-23T10:07:41Z)
• Adversarial AutoMixup [50.1874436169571]
  We propose AdAutomixup, an adversarial automatic mixup augmentation approach. It generates challenging samples to train a robust classifier for image classification. Our approach outperforms the state of the art in various classification scenarios.
  arXiv  Detail & Related papers  (2023-12-19T08:55:00Z)
• Image Processing and Machine Learning for Hyperspectral Unmixing: An Overview and the HySUPP Python Package [80.11512905623417]
  Unmixing estimates the fractional abundances of the endmembers within the pixel. This paper provides an overview of advanced and conventional unmixing approaches. We compare the performance of the unmixing techniques on three simulated and two real datasets.
  arXiv  Detail & Related papers  (2023-08-18T08:10:41Z)
• Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering [0.8543753708890495]
  In this paper, we realize mixture model-based clustering with a neural network. We train the network end-to-end via batch-wise EM iterations where the forward pass acts as the E-step and the backward pass acts as the M-step. Our trained networks outperform single-stage deep clustering methods that still depend on k-means.
  arXiv  Detail & Related papers  (2021-07-06T08:00:58Z)
• ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning [33.376639002442914]
  proposed training algorithm ScanMix, combines semantic clustering with semi-supervised learning (SSL) to improve the feature representations. ScanMix is designed based on the expectation maximisation (EM) framework, where the E-step estimates the value of a latent variable to cluster the training images. We show state-of-the-art results on standard benchmarks for symmetric, asymmetric and semantic label noise on CIFAR-10 and CIFAR-100, as well as large scale real label noise on WebVision.
  arXiv  Detail & Related papers  (2021-03-21T13:43:09Z)
• Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches [10.42820615166362]
  We evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings. We train a convolutional neural network to learn discriminative features by optimizing two popular versions of the Triplet Loss. We propose a new, simple Triplet Loss formulation, which shows desirable properties with respect to formal clustering objectives and outperforms the existing methods.
  arXiv  Detail & Related papers  (2020-07-06T23:38:14Z)
• Efficient Clustering for Stretched Mixtures: Landscape and Optimality [4.2111286819721485]
  This paper considers a canonical clustering problem where one receives unlabeled samples drawn from a balanced mixture of two elliptical distributions. We show that the non-optimal clustering function exhibits desirable geometric properties when the sample size exceeds some constant statistical objectives.
  arXiv  Detail & Related papers  (2020-03-22T17:57:07Z)
• Residual-Sparse Fuzzy $C$-Means Clustering Incorporating Morphological Reconstruction and Wavelet frames [146.63177174491082]
  Fuzzy $C$-Means (FCM) algorithm incorporates a morphological reconstruction operation and a tight wavelet frame transform. We present an improved FCM algorithm by imposing an $ell_0$ regularization term on the residual between the feature set and its ideal value. Experimental results reported for synthetic, medical, and color images show that the proposed algorithm is effective and efficient, and outperforms other algorithms.
  arXiv  Detail & Related papers  (2020-02-14T10:00:03Z)

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.