English
Related papers

Related papers: Generalized Kullback-Leibler Divergence Loss

200 papers

Weakly-supervised semantic segmentation aims to assign category labels to each pixel using weak annotations, significantly reducing manual annotation costs. Although existing methods have achieved remarkable progress in well-lit scenarios,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Chunyan Wang , Dong Zhang , Jinhui Tang

Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different distributions (denoted as $\mu$ and $\mu'$, respectively). In this work, we give an…

Machine Learning · Computer Science 2020-05-20 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu

Recent advances in Entity Resolution (ER) have leveraged Large Language Models (LLMs), achieving strong performance but at the cost of substantial computational resources or high financial overhead. Existing LLM-based ER approaches operate…

Databases · Computer Science 2026-02-06 Alexandros Zeakis , George Papadakis , Dimitrios Skoutas , Manolis Koubarakis

We investigate contrastive learning in the federated setting through the lens of SimCLR and multi-view mutual information maximization. In doing so, we uncover a connection between contrastive representation learning and user verification;…

Machine Learning · Computer Science 2024-05-06 Christos Louizos , Matthias Reisser , Denis Korzhenkov

Multi-instance partial-label learning (MIPL) is a weakly supervised framework that extends the principles of multi-instance learning (MIL) and partial-label learning (PLL) to address the challenges of inexact supervision in both instance…

Machine Learning · Computer Science 2025-12-22 Wei Tang , Yin-Fang Yang , Weijia Zhang , Min-Ling Zhang

Knowledge distillation has emerged as a scalable and effective way for privacy-preserving machine learning. One remaining drawback is that it consumes privacy in a model-level (i.e., client-level) manner, every distillation query incurs…

Cryptography and Security · Computer Science 2023-04-07 Yuntong Li , Shaowei Wang , Yingying Wang , Jin Li , Yuqiu Qian , Bangzhou Xin , Wei Yang

In the loss function of Variational Autoencoders there is a well known tension between two components: the reconstruction loss, improving the quality of the resulting images, and the Kullback-Leibler divergence, acting as a regularizer of…

Neural and Evolutionary Computing · Computer Science 2020-02-19 Andrea Asperti , Matteo Trentin

Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which erases undesirable information during training, and…

Machine Learning · Computer Science 2026-05-19 Puning Yang , Junchi Yu , Qizhou Wang , Philip Torr , Bo Han , Xiuying Chen

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…

Computation and Language · Computer Science 2025-08-05 Suhas Kamasetty Ramesh , Ayan Sengupta , Tanmoy Chakraborty

Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Mengya Gao , Yujun Shen , Quanquan Li , Junjie Yan , Liang Wan , Dahua Lin , Chen Change Loy , Xiaoou Tang

Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve…

Federated learning (FL) offers a privacy-preserving framework for distributed machine learning, enabling collaborative model training across diverse clients without centralizing sensitive data. However, statistical heterogeneity,…

Machine Learning · Statistics 2025-04-08 Hengrui Hu , Anai N. Kothari , Anjishnu Banerjee

Contrastive Language-Image Pre-training (CLIP) has achieved success on multiple downstream tasks by aligning image and text modalities. However, the nature of global contrastive learning limits CLIP's ability to comprehend compositional…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Xiaoxing Hu , Kaicheng Yang , Jun Wang , Haoran Xu , Ziyong Feng , Yupei Wang

Convolutional Neural Networks (ConvNets) have achieved excellent recognition performance in various visual recognition tasks. A large labeled training set is one of the most important factors for its success. However, it is difficult to…

Computer Vision and Pattern Recognition · Computer Science 2017-05-11 Bin-Bin Gao , Chao Xing , Chen-Wei Xie , Jianxin Wu , Xin Geng

We consider model-based reinforcement learning in finite Markov De- cision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by carrying out extended value it- erations under a constraint…

Machine Learning · Computer Science 2011-09-22 Sarah Filippi , Olivier Cappé , Aurélien Garivier

This paper proposes an ensemble learning model that is resistant to adversarial attacks. To build resilience, we introduced a training process where each member learns a radically distinct latent space. Member models are added one at a time…

Image and Video Processing · Electrical Eng. & Systems 2021-01-08 Ali Mirzaeian , Jana Kosecka , Houman Homayoun , Tinoosh Mohsenin , Avesta Sasan

Existing rotated object detectors are mostly inherited from the horizontal detection paradigm, as the latter has evolved into a well-developed area. However, these detectors are difficult to perform prominently in high-precision detection…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Xue Yang , Xiaojiang Yang , Jirui Yang , Qi Ming , Wentao Wang , Qi Tian , Junchi Yan

The soft Dice loss (SDL) has taken a pivotal role in numerous automated segmentation pipelines in the medical imaging community. Over the last years, some reasons behind its superior functioning have been uncovered and further optimizations…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Zifu Wang , Teodora Popordanoska , Jeroen Bertels , Robin Lemmens , Matthew B. Blaschko

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Nikolaos Giakoumoglou , Tania Stathaki

Inducing point Gaussian process approximations are often considered a gold standard in uncertainty estimation since they retain many of the properties of the exact GP and scale to large datasets. A major drawback is that they have…

Machine Learning · Computer Science 2022-03-08 Joost van Amersfoort , Lewis Smith , Andrew Jesson , Oscar Key , Yarin Gal