Related papers: A Similarity-based Framework for Classification Task

A Similarity-based Framework for Classification Task

URL: http://arxiv.org/abs/2203.02669v1
Date: Sat, 5 Mar 2022 06:39:50 GMT
Title: A Similarity-based Framework for Classification Task
Authors: Zhongchen Ma, and Songcan Chen
Abstract summary: 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.
Score: 21.182406977328267
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Similarity-based method gives rise to a new class of methods for multi-label learning and also achieves promising performance. In this paper, we generalize this method, resulting in a new framework for classification task. Specifically, we unite similarity-based learning and generalized linear models to achieve the best of both worlds. This allows us to capture interdependencies between classes and prevent from impairing performance of noisy classes. Each learned parameter of the model can reveal the contribution of one class to another, providing interpretability to some extent. Experiment results show the effectiveness of the proposed approach on multi-class and multi-label datasets

Related papers

Unsupervised Estimation of Ensemble Accuracy [0.0]
We present a method for estimating the joint power of several classifiers. It differs from existing approaches which focus on "diversity" measures by not relying on labels. We demonstrate the method on popular large-scale face recognition datasets.
arXiv Detail & Related papers (2023-11-18T02:31:36Z)
Convolutional autoencoder-based multimodal one-class classification [80.52334952912808]
One-class classification refers to approaches of learning using data from a single class only. We propose a deep learning one-class classification method suitable for multimodal data.
arXiv Detail & Related papers (2023-09-25T12:31:18Z)
Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection [58.48995335728938]
We learn three types of class-agnostic commonalities between base and novel classes explicitly. Our method can be readily integrated into most of existing fine-tuning based methods and consistently improve the performance by a large margin.
arXiv Detail & Related papers (2022-07-22T16:46:51Z)
Dual Path Structural Contrastive Embeddings for Learning Novel Objects [6.979491536753043]
Recent research shows that gaining information on a good feature space can be an effective solution to achieve favorable performance on few-shot tasks. We propose a simple but effective paradigm that decouples the tasks of learning feature representations and classifiers. Our method can still achieve promising results for both standard and generalized few-shot problems in either an inductive or transductive inference setting.
arXiv Detail & Related papers (2021-12-23T04:43:31Z)
Multi-Label Image Classification with Contrastive Learning [57.47567461616912]
We show that a direct application of contrastive learning can hardly improve in multi-label cases. We propose a novel framework for multi-label classification with contrastive learning in a fully supervised setting.
arXiv Detail & Related papers (2021-07-24T15:00:47Z)
Open-Set Representation Learning through Combinatorial Embedding [62.05670732352456]
We are interested in identifying novel concepts in a dataset through representation learning based on the examples in both labeled and unlabeled classes. We propose a learning approach, which naturally clusters examples in unseen classes using the compositional knowledge given by multiple supervised meta-classifiers on heterogeneous label spaces. The proposed algorithm discovers novel concepts via a joint optimization of enhancing the discrimitiveness of unseen classes as well as learning the representations of known classes generalizable to novel ones.
arXiv Detail & Related papers (2021-06-29T11:51:57Z)
Multi-Class Classification from Single-Class Data with Confidences [90.48669386745361]
We propose an empirical risk minimization framework that is loss-/model-/optimizer-independent. We show that our method can be Bayes-consistent with a simple modification even if the provided confidences are highly noisy.
arXiv Detail & Related papers (2021-06-16T15:38:13Z)
A Joint Representation Learning and Feature Modeling Approach for One-class Recognition [15.606362608483316]
We argue that both of these approaches have their own limitations; and a more effective solution can be obtained by combining the two. The proposed approach is based on the combination of a generative framework and a one-class classification method. We test the effectiveness of the proposed method on three one-class classification tasks and obtain state-of-the-art results.
arXiv Detail & Related papers (2021-01-24T19:51:46Z)
Learning and Evaluating Representations for Deep One-class Classification [59.095144932794646]
We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
arXiv Detail & Related papers (2020-11-04T23:33:41Z)
Meta Learning for Few-Shot One-class Classification [0.0]
We formulate the learning of meaningful features for one-class classification as a meta-learning problem. To learn these representations, we require only multiclass data from similar tasks. We validate our approach by adapting few-shot classification datasets to the few-shot one-class classification scenario.
arXiv Detail & Related papers (2020-09-11T11:35:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.