English
Related papers

Related papers: Improving Neural Response Diversity with Frequency…

200 papers

The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective. In this…

Skin disease classification from images is crucial to dermatological diagnosis. However, identifying skin lesions involves a variety of aspects in terms of size, color, shape, and texture. To make matters worse, many categories only contain…

Image and Video Processing · Electrical Eng. & Systems 2020-04-22 Wei Zhu , Haofu Liao , Wenbin Li , Weijian Li , Jiebo Luo

Face forgery detection is raising ever-increasing interest in computer vision since facial manipulation technologies cause serious worries. Though recent works have reached sound achievements, there are still unignorable problems: a)…

Computer Vision and Pattern Recognition · Computer Science 2021-03-17 Jiaming Li , Hongtao Xie , Jiahong Li , Zhongyuan Wang , Yongdong Zhang

Large language models (LLMs) have been garnering increasing attention in the recommendation community. Some studies have observed that LLMs, when fine-tuned by the cross-entropy (CE) loss with a full softmax, could achieve…

Information Retrieval · Computer Science 2024-08-27 Cong Xu , Zhangchi Zhu , Mo Yu , Jun Wang , Jianyong Wang , Wei Zhang

The data-to-equation (Data2Eqn) task aims to discover interpretable mathematical equations that map observed values to labels, offering physical insights and broad applicability across academic and industrial domains. Genetic programming…

Machine Learning · Computer Science 2025-05-22 Wangyang Ying , Haoyue Bai , Nanxu Gong , Xinyuan Wang , Sixun Dong , Haifeng Chen , Yanjie Fu

Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…

Machine Learning · Computer Science 2026-04-13 Matheus Vinícius Todescato , Joel Luís Carbonera

Self-training methods have proven to be effective in exploiting abundant unlabeled data in semi-supervised learning, particularly when labeled data is scarce. While many of these approaches rely on a cross-entropy loss function (CE), recent…

Machine Learning · Computer Science 2024-09-12 Aurelien Gauffre , Julien Horvat , Massih-Reza Amini

Researchers have recently started investigating deep neural networks for dialogue applications. In particular, generative sequence-to-sequence (Seq2Seq) models have shown promising results for unstructured tasks, such as word-level dialogue…

Computation and Language · Computer Science 2016-11-21 Iulian Vlad Serban , Ryan Lowe , Laurent Charlin , Joelle Pineau

This paper proposes a model for transforming speech features using the frequency-directional attention model for End-to-End (E2E) automatic speech recognition. The idea is based on the hypothesis that in the phoneme system of each language,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-30 Akihiro Dobashi , Chee Siang Leow , Hiromitsu Nishizaki

In practical applications of regression analysis, it is not uncommon to encounter a multitude of values for each attribute. In such a situation, the univariate distribution, which is typically Gaussian, is suboptimal because the mean may be…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Krzysztof Byrski , Jacek Tabor , Przemysław Spurek , Marcin Mazur

Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches,…

Computation and Language · Computer Science 2019-06-19 Anusha Balakrishnan , Jinfeng Rao , Kartikeya Upasani , Michael White , Rajen Subba

End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases. In this paper, we propose a novel yet simple end-to-end differentiable model called memory-to-sequence (Mem2Seq) to address this…

Computation and Language · Computer Science 2018-05-22 Andrea Madotto , Chien-Sheng Wu , Pascale Fung

Deep learning-based models generalize better to unknown data samples after being guided "where to look" by incorporating human perception into training strategies. We made an observation that the entropy of the model's salience trained in…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Jacob Piland , Adam Czajka , Christopher Sweet

The estimation of rare event or failure probabilities in high dimensions is of interest in many areas of science and technology. We consider problems where the rare event is expressed in terms of a computationally costly numerical model.…

Computation · Statistics 2020-06-11 Felipe Uribe , Iason Papaioannou , Youssef M. Marzouk , Daniel Straub

Multi-sequence MRIs can be necessary for reliable diagnosis in clinical practice due to the complimentary information within sequences. However, redundant information exists across sequences, which interferes with mining efficient…

Computer Vision and Pattern Recognition · Computer Science 2023-02-02 Luyi Han , Tao Tan , Tianyu Zhang , Yunzhi Huang , Xin Wang , Yuan Gao , Jonas Teuwen , Ritse Mann

Supervised Fine-Tuning (SFT) is essential for aligning Large Language Models (LLMs) with user intent, yet it is believed to suppress generative diversity. Although this reduction is frequently referenced, formal empirical testing of the…

Machine Learning · Computer Science 2026-05-12 Roman Klypa , Oleksandr Cherednichenko

This paper presents an experimental analysis about trade-offs in top-k classification accuracies on losses for deep leaning and proposal of a novel top-k loss. Commonly-used cross entropy (CE) is not guaranteed to optimize top-k prediction…

Machine Learning · Computer Science 2020-07-31 Azusa Sawada , Eiji Kaneko , Kazutoshi Sagi

Dialogue generation models face the challenge of producing generic and repetitive responses. Unlike previous augmentation methods that mostly focus on token manipulation and ignore the essential variety within a single sample using hard…

Computation and Language · Computer Science 2021-03-03 Yu Cao , Liang Ding , Zhiliang Tian , Meng Fang

Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencies that can contribute to costly training dynamics. The…

Machine Learning · Computer Science 2026-04-30 Maxwell Miller-Golub , Collin Coil , Kamil Faber , Marcin Pietron , Panpan Zheng , Pasquale Minervini , Roberto Corizzo

Accent classification or AC is a task to predict the accent type of an input utterance, and it can be used as a preliminary step toward accented speech recognition and accent conversion. Existing studies have often achieved such…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-02 Chihiro Watanabe , Hirokazu Kameoka
‹ Prev 1 4 5 6 7 8 10 Next ›