中文
相关论文

相关论文: Mixed-Precision Information Bottlenecks for On-Dev…

200 篇论文

Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot research topic. Existing works generally take into account disentangling speech components through human-crafted…

声音 · 计算机科学 2024-05-01 Ziqi Liang , Jianzong Wang , Xulong Zhang , Yong Zhang , Ning Cheng , Jing Xiao

Deep neural networks (DNNs) have achieved significant success in various applications with large-scale and balanced data. However, data in real-world visual recognition are usually long-tailed, bringing challenges to efficient training and…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Yifan Lan , Xin Cai , Jun Cheng , Shan Tan

The Information Bottleneck (IB) principle facilitates effective representation learning by preserving label-relevant information while compressing irrelevant information. However, its strong reliance on accurate labels makes it inherently…

机器学习 · 计算机科学 2025-12-12 Yi Huang , Qingyun Sun , Yisen Gao , Haonan Yuan , Xingcheng Fu , Jianxin Li

The information bottleneck (IB) method is a technique for extracting information that is relevant for predicting the target random variable from the source random variable, which is typically implemented by optimizing the IB Lagrangian that…

机器学习 · 计算机科学 2020-12-23 Ziqi Pan , Li Niu , Jianfu Zhang , Liqing Zhang

Multimodal sentiment analysis has received significant attention across diverse research domains. Despite advancements in algorithm design, existing approaches suffer from two critical limitations: insufficient learning of…

人工智能 · 计算机科学 2025-11-04 Huiting Huang , Tieliang Gong , Kai He , Jialun Wu , Erik Cambria , Mengling Feng

Domain mismatch problem caused by speaker-unrelated feature has been a major topic in speaker recognition. In this paper, we propose an explicit disentanglement framework to unravel speaker-relevant features from speaker-unrelated features…

音频与语音处理 · 电气工程与系统科学 2022-10-13 Sung Hwan Mun , Min Hyun Han , Minchan Kim , Dongjune Lee , Nam Soo Kim

Learning effective joint embedding for cross-modal data has always been a focus in the field of multimodal machine learning. We argue that during multimodal fusion, the generated multimodal embedding may be redundant, and the discriminative…

机器学习 · 计算机科学 2022-12-06 Sijie Mai , Ying Zeng , Haifeng Hu

The information bottleneck (IB) principle has been adopted to explain deep learning in terms of information compression and prediction, which are balanced by a trade-off hyperparameter. How to optimize the IB principle for better robustness…

机器学习 · 计算机科学 2021-03-04 Penglong Zhai , Shihua Zhang

Data errors, corruptions, and poisoning attacks during training pose a major threat to the reliability of modern AI systems. While extensive effort has gone into empirical mitigations, the evolving nature of attacks and the complexity of…

机器学习 · 计算机科学 2025-10-28 Tobias Lorenz , Marta Kwiatkowska , Mario Fritz

Collaborative edge sensing systems, particularly in collaborative perception systems in autonomous driving, can significantly enhance tracking accuracy and reduce blind spots with multi-view sensing capabilities. However, their limited…

网络与互联网体系结构 · 计算机科学 2024-09-02 Zhengru Fang , Senkang Hu , Liyan Yang , Yiqin Deng , Xianhao Chen , Yuguang Fang

The information bottleneck (IB) principle has been suggested as a way to analyze deep neural networks. The learning dynamics are studied by inspecting the mutual information (MI) between the hidden layers and the input and output. Notably,…

机器学习 · 计算机科学 2022-02-15 Stephan Sloth Lorenzen , Christian Igel , Mads Nielsen

Speaker diarization is an important problem that is topical, and is especially useful as a preprocessor for conversational speech related applications. The objective of this paper is two-fold: (i) segment initialization by uniformly…

音频与语音处理 · 电气工程与系统科学 2021-03-05 Nauman Dawalatabad , Srikanth Madikeri , C. Chandra Sekhar , Hema A. Murthy

Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks…

声音 · 计算机科学 2026-04-02 Xiaoxu Zhu , Junhua Li , Aaron J. Li , Guangchao Yao , Xiaojie Yu

Effectively leveraging multimodal data such as various images, laboratory tests and clinical information is gaining traction in a variety of AI-based medical diagnosis and prognosis tasks. Most existing multi-modal techniques only focus on…

图像与视频处理 · 电气工程与系统科学 2023-11-28 Yingying Fang , Shuang Wu , Sheng Zhang , Chaoyan Huang , Tieyong Zeng , Xiaodan Xing , Simon Walsh , Guang Yang

The information bottleneck (IB) problem is a widely studied framework in machine learning for extracting compressed features that are informative for downstream tasks. However, current approaches to solving the IB problem rely on a…

信息论 · 计算机科学 2024-10-11 Amirmohammad Farzaneh , Osvaldo Simeone

Collaborative perception systems leverage multiple edge devices, such surveillance cameras or autonomous cars, to enhance sensing quality and eliminate blind spots. Despite their advantages, challenges such as limited channel capacity and…

网络与互联网体系结构 · 计算机科学 2025-01-07 Zhengru Fang , Senkang Hu , Jingjing Wang , Yiqin Deng , Xianhao Chen , Yuguang Fang

In recent several years, the information bottleneck (IB) principle provides an information-theoretic framework for deep multi-view clustering (MVC) by compressing multi-view observations while preserving the relevant information of multiple…

信息论 · 计算机科学 2024-03-26 Xiaoqiang Yan , Zhixiang Jin , Fengshou Han , Yangdong Ye

This paper addresses the inherent limitations of conventional bottleneck structures (diminished instance discriminability due to overemphasis on batch statistics) and decoupled heads (computational redundancy) in object detection frameworks…

计算机视觉与模式识别 · 计算机科学 2025-07-30 Lin Huang , Yujuan Tan , Weisheng Li , Shitai Shan , Liu Liu , Linlin Shen , Jing Yu , Yue Niu

Recent evidence suggests that modeling higher-order interactions (HOIs) in functional magnetic resonance imaging (fMRI) data can enhance the diagnostic accuracy of machine learning systems. However, effectively extracting and utilizing HOIs…

机器学习 · 计算机科学 2025-11-04 Kunyu Zhang , Qiang Li , Shujian Yu

Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two…

信息论 · 计算机科学 2023-11-08 Yuyan Ni , Yanyan Lan , Ao Liu , Zhiming Ma
‹ 上一页 1 2 3 10 下一页 ›