English
Related papers

Related papers: OSLNet: Deep Small-Sample Classification with an O…

200 papers

Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-class similarity nor inter-class margin of the learned deep…

Computer Vision and Pattern Recognition · Computer Science 2017-12-06 José Lezama , Qiang Qiu , Pablo Musé , Guillermo Sapiro

ASR systems are deployed across diverse environments, each with specific hardware constraints. We use supernet training to jointly train multiple encoders of varying sizes, enabling dynamic model size adjustment to fit hardware constraints…

Computation and Language · Computer Science 2025-02-05 Jingjing Xu , Eugen Beck , Zijian Yang , Ralf Schlüter

Open-Set Classification (OSC) intends to adapt closed-set classification models to real-world scenarios, where the classifier must correctly label samples of known classes while rejecting previously unseen unknown samples. Only recently,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-19 Andres Palechor , Annesha Bhoumik , Manuel Günther

This study investigates an application of a new probabilistic interpretation of a softmax output to Open-Set Recognition (OSR). Softmax is a mechanism wildly used in classification and object recognition. However, a softmax mechanism forces…

Computer Vision and Pattern Recognition · Computer Science 2021-11-01 Tatpong Katanyukul , Pisit Nakjai

The dramatic growth of big datasets presents a new challenge to data storage and analysis. Data reduction, or subsampling, that extracts useful information from datasets is a crucial step in big data analysis. We propose an orthogonal…

Methodology · Statistics 2021-06-01 Lin Wang , Jake Elmstedt , Weng Kee Wong , Hongquan Xu

Orthogonal matrix has shown advantages in training Recurrent Neural Networks (RNNs), but such matrix is limited to be square for the hidden-to-hidden transformation in RNNs. In this paper, we generalize such square orthogonal matrix to…

Machine Learning · Computer Science 2017-11-22 Lei Huang , Xianglong Liu , Bo Lang , Adams Wei Yu , Yongliang Wang , Bo Li

Unknown examples that are unseen during training often appear in real-world machine learning tasks, and an intelligent self-learning system should be able to distinguish between known and unknown examples. Accordingly, open set recognition…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Jaeyeon Jang , Chang Ouk Kim

This study explores the learning dynamics of neural networks by analyzing the singular value decomposition (SVD) of their weights throughout training. Our investigation reveals that an orthogonal basis within each multidimensional weight's…

Machine Learning · Computer Science 2024-11-12 Daniel Coquelin , Katharina Flügel , Marie Weiel , Nicholas Kiefer , Charlotte Debus , Achim Streit , Markus Götz

Neural networks are susceptible to artificially designed adversarial perturbations. Recent efforts have shown that imposing certain modifications on classification layer can improve the robustness of the neural networks. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2021-09-27 Cong Xu , Xiang Li , Min Yang

Label smoothing is an effective regularization tool for deep neural networks (DNNs), which generates soft labels by applying a weighted average between the uniform distribution and the hard label. It is often used to reduce the overfitting…

Computer Vision and Pattern Recognition · Computer Science 2021-07-23 Chang-Bin Zhang , Peng-Tao Jiang , Qibin Hou , Yunchao Wei , Qi Han , Zhen Li , Ming-Ming Cheng

Enforcing orthonormal or isometric property for the weight matrices has been shown to enhance the training of deep neural networks by mitigating gradient exploding/vanishing and increasing the robustness of the learned networks. However,…

Machine Learning · Computer Science 2024-03-01 Zhen Qin , Xuwei Tan , Zhihui Zhu

Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large…

Machine Learning · Computer Science 2019-12-05 Xinshao Wang , Yang Hua , Elyor Kodirov , Guosheng Hu , Neil M. Robertson

Deep neural networks have achieved remarkable performance on a range of classification tasks, with softmax cross-entropy (CE) loss emerging as the de-facto objective function. The CE loss encourages features of a class to have a higher…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Kanchana Ranasinghe , Muzammal Naseer , Munawar Hayat , Salman Khan , Fahad Shahbaz Khan

The goal for classification is to correctly assign labels to unseen samples. However, most methods misclassify samples with unseen labels and assign them to one of the known classes. Open-Set Classification (OSC) algorithms aim to maximize…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Halil Bisgin , Andres Palechor , Mike Suter , Manuel Günther

Deep learning models, especially convolutional neural networks, have achieved impressive results in medical image classification. However, these models often produce overconfident predictions, which can undermine their reliability in…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Kushan Choudhury , Shubhrodeep Roy , Ankur Chanda , Shubhajit Biswas , Somenath Kuiry

In this paper, we explore ordinal classification (in the context of deep neural networks) through a simple modification of the squared error loss which not only allows it to not only be sensitive to class ordering, but also allows the…

Machine Learning · Statistics 2017-01-10 Christopher Beckham , Christopher Pal

We propose a kernelized classification layer for deep networks. Although conventional deep networks introduce an abundance of nonlinearity for representation (feature) learning, they almost universally use a linear classifier on the learned…

Machine Learning · Computer Science 2021-03-22 Sadeep Jayasumana , Srikumar Ramalingam , Sanjiv Kumar

In open-set recognition (OSR), classifiers should be able to reject unknown-class samples while maintaining high closed-set classification accuracy. To effectively solve the OSR problem, previous studies attempted to limit latent feature…

Computer Vision and Pattern Recognition · Computer Science 2022-07-22 Wonwoo Cho , Jaegul Choo

Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and…

Machine Learning · Computer Science 2015-02-24 Yichuan Tang

Most image segmentation algorithms are trained on binary masks formulated as a classification task per pixel. However, in applications such as medical imaging, this "black-and-white" approach is too constraining because the contrast between…

Image and Video Processing · Electrical Eng. & Systems 2020-11-19 Charley Gros , Andreanne Lemay , Julien Cohen-Adad
‹ Prev 1 2 3 10 Next ›