Semi-Supervised Metric Learning: A Deep Resurrection

• URL: http://arxiv.org/abs/2105.05061v1
• Date: Mon, 10 May 2021 12:28:45 GMT
• Title: Semi-Supervised Metric Learning: A Deep Resurrection
• Authors: Ujjal Kr Dutta, Mehrtash Harandi, Chellu Chandra Sekhar
• Abstract summary: Semi-Supervised DML (SSDML) tries to learn a metric using a few labeled examples, and abundantly available unlabeled examples. We propose a graph-based approach that first propagates the affinities between the pairs of examples. We impose Metricity constraint on the metric parameters, as it leads to a better performance.
• Score: 22.918651280720855
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Distance Metric Learning (DML) seeks to learn a discriminative embedding where similar examples are closer, and dissimilar examples are apart. In this paper, we address the problem of Semi-Supervised DML (SSDML) that tries to learn a metric using a few labeled examples, and abundantly available unlabeled examples. SSDML is important because it is infeasible to manually annotate all the examples present in a large dataset. Surprisingly, with the exception of a few classical approaches that learn a linear Mahalanobis metric, SSDML has not been studied in the recent years, and lacks approaches in the deep SSDML scenario. In this paper, we address this challenging problem, and revamp SSDML with respect to deep learning. In particular, we propose a stochastic, graph-based approach that first propagates the affinities between the pairs of examples from labeled data, to that of the unlabeled pairs. The propagated affinities are used to mine triplet based constraints for metric learning. We impose orthogonality constraint on the metric parameters, as it leads to a better performance by avoiding a model collapse.

Related papers

• Characterizing Datapoints via Second-Split Forgetting [93.99363547536392]
  We propose $$-second-$split$ $forgetting$ $time$ (SSFT), a complementary metric that tracks the epoch (if any) after which an original training example is forgotten. We demonstrate that $mislabeled$ examples are forgotten quickly, and seemingly $rare$ examples are forgotten comparatively slowly. SSFT can (i) help to identify mislabeled samples, the removal of which improves generalization; and (ii) provide insights about failure modes.
  arXiv  Detail & Related papers  (2022-10-26T21:03:46Z)
• ELM: Embedding and Logit Margins for Long-Tail Learning [70.19006872113862]
  Long-tail learning is the problem of learning under skewed label distributions. We present Embedding and Logit Margins (ELM), a unified approach to enforce margins in logit space. The ELM method is shown to perform well empirically, and results in tighter tail class embeddings.
  arXiv  Detail & Related papers  (2022-04-27T21:53:50Z)
• Adaptive neighborhood Metric learning [184.95321334661898]
  We propose a novel distance metric learning algorithm, named adaptive neighborhood metric learning (ANML) ANML can be used to learn both the linear and deep embeddings. The emphlog-exp mean function proposed in our method gives a new perspective to review the deep metric learning methods.
  arXiv  Detail & Related papers  (2022-01-20T17:26:37Z)
• Dash: Semi-Supervised Learning with Dynamic Thresholding [72.74339790209531]
  We propose a semi-supervised learning (SSL) approach that uses unlabeled examples to train models. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection.
  arXiv  Detail & Related papers  (2021-09-01T23:52:29Z)
• Exploring Adversarial Robustness of Deep Metric Learning [25.12224002984514]
  DML uses deep neural architectures to learn semantic embeddings of the input. We tackle the primary challenge of the metric losses being dependent on the samples in a mini-batch. Using experiments on three commonly-used DML datasets, we demonstrate 5-76 fold increases in adversarial accuracy.
  arXiv  Detail & Related papers  (2021-02-14T23:18:12Z)
• Multimodal-Aware Weakly Supervised Metric Learning with Self-weighting Triplet Loss [2.010312620798609]
  We propose a novel weakly supervised metric learning algorithm, named MultimoDal Aware weakly supervised Metric Learning (MDaML) MDaML partitions the data space into several clusters and allocates the local cluster centers and weight for each sample. Experiments conducted on 13 datasets validate the superiority of the proposed MDaML.
  arXiv  Detail & Related papers  (2021-02-03T07:27:05Z)
• Attentional-Biased Stochastic Gradient Descent [74.49926199036481]
  We present a provable method (named ABSGD) for addressing the data imbalance or label noise problem in deep learning. Our method is a simple modification to momentum SGD where we assign an individual importance weight to each sample in the mini-batch. ABSGD is flexible enough to combine with other robust losses without any additional cost.
  arXiv  Detail & Related papers  (2020-12-13T03:41:52Z)
• Unsupervised Deep Metric Learning via Orthogonality based Probabilistic Loss [27.955068939695042]
  Existing state-of-the-art metric learning approaches require class labels to learn a metric. We propose an unsupervised approach that learns a metric without making use of class labels. The pseudo-labels are used to form triplets of examples, which guide the metric learning.
  arXiv  Detail & Related papers  (2020-08-22T17:13:33Z)
• Positive semidefinite support vector regression metric learning [0.0]
  RAML framework is proposed to handle the metric learning problem in those scenarios. It can't learn positive semidefinite distance metric which is necessary in metric learning. We propose two methds to overcame the weakness.
  arXiv  Detail & Related papers  (2020-08-18T04:45:59Z)
• Robust and On-the-fly Dataset Denoising for Image Classification [72.10311040730815]
  On-the-fly Data Denoising (ODD) is robust to mislabeled examples, while introducing almost zero computational overhead compared to standard training. ODD is able to achieve state-of-the-art results on a wide range of datasets including real-world ones such as WebVision and Clothing1M.
  arXiv  Detail & Related papers  (2020-03-24T03:59:26Z)

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.