English
Related papers

Related papers: Learning Discriminative Features Via Weights-biase…

200 papers

In face recognition, designing margin-based (e.g., angular, additive, additive angular margins) softmax loss functions plays an important role in learning discriminative features. However, these hand-crafted heuristic methods are…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Xiaobo Wang , Shuo Wang , Cheng Chi , Shifeng Zhang , Tao Mei

Neural collapse (NC) describes the structured geometry that emerges in the features and weights of trained classifiers. Recent theory suggests NC can be suboptimal in deep architectures, attributing this to an explicit low-rank bias from L2…

Machine Learning · Computer Science 2026-05-25 Connall Garrod , Jonathan P. Keating , Christos Thrampoulidis

We present a latent variable model for classification that provides a novel probabilistic interpretation of neural network softmax classifiers. We derive a variational objective to train the model, analogous to the evidence lower bound…

Machine Learning · Computer Science 2024-01-10 Shehzaad Dhuliawala , Mrinmaya Sachan , Carl Allen

The Softmax function is used in the final layer of nearly all existing sequence-to-sequence models for language generation. However, it is usually the slowest layer to compute which limits the vocabulary size to a subset of most frequent…

Computation and Language · Computer Science 2019-03-25 Sachin Kumar , Yulia Tsvetkov

Distance metric learning (DML) is to learn the embeddings where examples from the same class are closer than examples from different classes. It can be cast as an optimization problem with triplet constraints. Due to the vast number of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-16 Qi Qian , Lei Shang , Baigui Sun , Juhua Hu , Hao Li , Rong Jin

Speech emotion recognition is an important aspect of human-computer interaction. Prior work proposes various end-to-end models to improve the classification performance. However, most of them rely on the cross-entropy loss together with…

Computer Vision and Pattern Recognition · Computer Science 2019-10-25 Zheng Lian , Ya Li , Jianhua Tao , Jian Huang

Convolutional neural networks (CNNs) have been demonstrated their powerful ability to extract discriminative features for hyperspectral image classification. However, general deep learning methods for CNNs ignore the influence of complex…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Zhiqiang Gong , Xian Zhou , Wen Yao

The purpose of feature extraction on convolutional neural networks is to reuse deep representations learnt for a pre-trained model to solve a new, potentially unrelated problem. However, raw feature extraction from all layers is unfeasible…

Neural and Evolutionary Computing · Computer Science 2019-11-11 Victor Gimenez-Abalos , Armand Vilalta , Dario Garcia-Gasulla , Jesus Labarta , Eduard Ayguadé

Few-shot classification algorithms can alleviate the data scarceness issue, which is vital in many real-world problems, by adopting models pre-trained from abundant data in other domains. However, the pre-training process was commonly…

Machine Learning · Computer Science 2020-03-03 Chao Wang , Ruo-Ze Liu , Han-Jia Ye , Yang Yu

Soft targets combined with the cross-entropy loss have shown to improve generalization performance of deep neural networks on supervised classification tasks. The standard cross-entropy loss however assumes data to be categorically…

Machine Learning · Computer Science 2024-07-16 Johannes Hugger , Virginie Uhlmann

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

Current research in Computer Vision has shown that Convolutional Neural Networks (CNN) give state-of-the-art performance in many classification tasks and Computer Vision problems. The embedding of CNN, which is the internal representation…

Computer Vision and Pattern Recognition · Computer Science 2015-08-04 Axel Angel

Despite being the standard loss function to train multi-class neural networks, the log-softmax has two potential limitations. First, it involves computations that scale linearly with the number of output classes, which can restrict the size…

Machine Learning · Computer Science 2016-05-30 Alexandre de Brébisson , Pascal Vincent

In knowledge graph embedding, the theoretical relationship between the softmax cross-entropy and negative sampling loss functions has not been investigated. This makes it difficult to fairly compare the results of the two different loss…

Machine Learning · Computer Science 2022-03-17 Hidetaka Kamigaito , Katsuhiko Hayashi

The Softmax function on top of a final linear layer is the de facto method to output probability distributions in neural networks. In many applications such as language models or text generation, this model has to produce distributions over…

Machine Learning · Computer Science 2019-05-15 Octavian-Eugen Ganea , Sylvain Gelly , Gary Bécigneul , Aliaksei Severyn

Modern neural network architectures for large-scale learning tasks have substantially higher model complexities, which makes understanding, visualizing and training these architectures difficult. Recent contributions to deep learning…

Machine Learning · Computer Science 2024-10-30 Jayadeva , Himanshu Pant , Mayank Sharma , Abhimanyu Dubey , Sumit Soman , Suraj Tripathi , Sai Guruju , Nihal Goalla

Features obtained from object recognition CNNs have been widely used for measuring perceptual similarities between images. Such differentiable metrics can be used as perceptual learning losses to train image enhancement models. However, the…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Mauricio Delbracio , Hossein Talebi , Peyman Milanfar

Sampling-based methods, e.g., Deep Ensembles and Bayesian Neural Nets have become promising approaches to improve the quality of uncertainty estimation and robust generalization. However, they suffer from a large model size and high latency…

Machine Learning · Computer Science 2024-05-29 Ha Manh Bui , Anqi Liu

This paper addresses deep face recognition (FR) problem under open-set protocol, where ideal face features are expected to have smaller maximal intra-class distance than minimal inter-class distance under a suitably chosen metric space.…

Computer Vision and Pattern Recognition · Computer Science 2018-01-31 Weiyang Liu , Yandong Wen , Zhiding Yu , Ming Li , Bhiksha Raj , Le Song

Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks, where now excessively large models are used. However, such models face several problems during the…

Machine Learning · Computer Science 2021-09-21 Alexander Kovalenko , Pavel Kordík , Magda Friedjungová