Leveraging Class Hierarchies with Metric-Guided Prototype Learning

• URL: http://arxiv.org/abs/2007.03047v3
• Date: Mon, 29 Nov 2021 14:07:06 GMT
• Title: Leveraging Class Hierarchies with Metric-Guided Prototype Learning
• Authors: Vivien Sainte Fare Garnot and Loic Landrieu
• Abstract summary: In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under the form of a cost matrix. We propose to model the hierarchical class structure by integrating this metric in the supervision of a prototypical network.
• Score: 5.070542698701158
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In many classification tasks, the set of target classes can be organized into a hierarchy. This structure induces a semantic distance between classes, and can be summarised under the form of a cost matrix, which defines a finite metric on the class set. In this paper, we propose to model the hierarchical class structure by integrating this metric in the supervision of a prototypical network. Our method relies on jointly learning a feature-extracting network and a set of class prototypes whose relative arrangement in the embedding space follows an hierarchical metric. We show that this approach allows for a consistent improvement of the error rate weighted by the cost matrix when compared to traditional methods and other prototype-based strategies. Furthermore, when the induced metric contains insight on the data structure, our method improves the overall precision as well. Experiments on four different public datasets - from agricultural time series classification to depth image semantic segmentation - validate our approach.

Related papers

• From Logits to Hierarchies: Hierarchical Clustering made Simple [16.132657141993548]
  We show that a lightweight procedure implemented on top of pre-trained non-hierarchical clustering models outperforms models designed specifically for hierarchical clustering. Our proposed approach is computationally efficient and applicable to any pre-trained clustering model that outputs logits, without requiring any fine-tuning.
  arXiv  Detail & Related papers  (2024-10-10T12:27:45Z)
• A Fixed-Point Approach to Unified Prompt-Based Counting [51.20608895374113]
  This paper aims to establish a comprehensive prompt-based counting framework capable of generating density maps for objects indicated by various prompt types, such as box, point, and text. Our model excels in prominent class-agnostic datasets and exhibits superior performance in cross-dataset adaptation tasks.
  arXiv  Detail & Related papers  (2024-03-15T12:05:44Z)
• Exploiting Data Hierarchy as a New Modality for Contrastive Learning [0.0]
  This work investigates how hierarchically structured data can help neural networks learn conceptual representations of cathedrals. The underlying WikiScenes dataset provides a spatially organized hierarchical structure of cathedral components. We propose a novel hierarchical contrastive training approach that leverages a triplet margin loss to represent the data's spatial hierarchy in the encoder's latent space.
  arXiv  Detail & Related papers  (2024-01-06T21:47:49Z)
• Generating Hierarchical Structures for Improved Time Series Classification Using Stochastic Splitting Functions [0.0]
  This study introduces a novel hierarchical divisive clustering approach with splitting functions (SSFs) to enhance classification performance in multi-class datasets through hierarchical classification (HC) The method has the unique capability of generating hierarchy without requiring explicit information, making it suitable for datasets lacking prior knowledge of hierarchy.
  arXiv  Detail & Related papers  (2023-09-21T10:34:50Z)
• Hierarchical clustering with dot products recovers hidden tree structure [53.68551192799585]
  In this paper we offer a new perspective on the well established agglomerative clustering algorithm, focusing on recovery of hierarchical structure. We recommend a simple variant of the standard algorithm, in which clusters are merged by maximum average dot product and not, for example, by minimum distance or within-cluster variance. We demonstrate that the tree output by this algorithm provides a bona fide estimate of generative hierarchical structure in data, under a generic probabilistic graphical model.
  arXiv  Detail & Related papers  (2023-05-24T11:05:12Z)
• Inspecting class hierarchies in classification-based metric learning models [0.0]
  We train a softmax classifier and three metric learning models with several training options on benchmark and real-world datasets. We evaluate the hierarchical inference performance by inspecting learned class representatives and the hierarchy-informed performance, i.e., the classification performance, and the metric learning performance by considering predefined hierarchical structures.
  arXiv  Detail & Related papers  (2023-01-26T12:40:12Z)
• A Similarity-based Framework for Classification Task [21.182406977328267]
  Similarity-based method gives rise to a new class of methods for multi-label learning and also achieves promising performance. We unite similarity-based learning and generalized linear models to achieve the best of both worlds.
  arXiv  Detail & Related papers  (2022-03-05T06:39:50Z)
• Contextualizing Meta-Learning via Learning to Decompose [125.76658595408607]
  We propose Learning to Decompose Network (LeadNet) to contextualize the meta-learned support-to-target'' strategy. LeadNet learns to automatically select the strategy associated with the right via incorporating the change of comparison across contexts with polysemous embeddings.
  arXiv  Detail & Related papers  (2021-06-15T13:10:56Z)
• Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification [94.55805516167369]
  We propose a new approach for binary classification from m U-sets for $mge2$. Our key idea is to consider an auxiliary classification task called surrogate set classification (SSC)
  arXiv  Detail & Related papers  (2021-02-01T07:36:38Z)
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
  Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain. We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one. Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
  arXiv  Detail & Related papers  (2020-12-08T08:52:00Z)
• Structured Graph Learning for Clustering and Semi-supervised Classification [74.35376212789132]
  We propose a graph learning framework to preserve both the local and global structure of data. Our method uses the self-expressiveness of samples to capture the global structure and adaptive neighbor approach to respect the local structure. Our model is equivalent to a combination of kernel k-means and k-means methods under certain condition.
  arXiv  Detail & Related papers  (2020-08-31T08:41:20Z)

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.