English
Related papers

Related papers: Decoupled Kullback-Leibler Divergence Loss

200 papers

This paper provides a unified perspective for the Kullback-Leibler (KL)-divergence and the integral probability metrics (IPMs) from the perspective of maximum likelihood density-ratio estimation (DRE). Both the KL-divergence and the IPMs…

Machine Learning · Computer Science 2022-02-01 Masahiro Kato , Masaaki Imaizumi , Kentaro Minami

Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Nicholas Cooper , Lijun Chen , Sailesh Dwivedy , Danna Gurari

Knowledge distillation (KD) exploits a large well-trained model (i.e., teacher) to train a small student model on the same dataset for the same task. Treating teacher features as knowledge, prevailing methods of knowledge distillation train…

Computer Vision and Pattern Recognition · Computer Science 2023-05-29 Yuzhu Wang , Lechao Cheng , Manni Duan , Yongheng Wang , Zunlei Feng , Shu Kong

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…

Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. To…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Yongheng Zhang , Danfeng Yan

We study concentration inequalities for the Kullback--Leibler (KL) divergence between the empirical distribution and the true distribution. Applying a recursion technique, we improve over the method of types bound uniformly in all regimes…

Information Theory · Computer Science 2019-10-22 Jay Mardia , Jiantao Jiao , Ervin Tánczos , Robert D. Nowak , Tsachy Weissman

Adversarial training is the most effective defense against adversarial attacks. The effectiveness of the adversarial attacks has been on the design of its loss function and regularization term. The most widely used loss function in…

Machine Learning · Computer Science 2025-10-08 Zhenyu Liu , Varun Ojha

Despite exciting progress in pre-training for visual-linguistic (VL) representations, very few aspire to a small VL model. In this paper, we study knowledge distillation (KD) to effectively compress a transformer-based large VL model into a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Zhiyuan Fang , Jianfeng Wang , Xiaowei Hu , Lijuan Wang , Yezhou Yang , Zicheng Liu

Despite the success of two-stage few-shot classification methods, in the episodic meta-training stage, the model suffers severe overfitting. We hypothesize that it is caused by over-discrimination, i.e., the model learns to over-rely on the…

Machine Learning · Computer Science 2023-07-10 Siqi Hui , Sanping Zhou , Ye deng , Jinjun Wang

Real-world data usually suffers from severe class imbalance and long-tailed distributions, where minority classes are significantly underrepresented compared to the majority ones. Recent research prefers to utilize multi-expert…

Computer Vision and Pattern Recognition · Computer Science 2023-05-08 Zhengzhuo Xu , Zenghao Chai , Chengyin Xu , Chun Yuan , Haiqin Yang

Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…

Machine Learning · Computer Science 2023-01-31 Aref Jafari , Mehdi Rezagholizadeh , Ali Ghodsi

Conflicting objectives present a considerable challenge in interleaving multi-task learning, necessitating the need for meticulous design and balance to ensure effective learning of a representative latent data space across all tasks…

Machine Learning · Computer Science 2025-01-17 Noelle Y. L. Wong , Eng Yeow Cheu , Zhonglin Chiam , Dipti Srinivasan

Federated Learning often relies on sharing full or partial model weights, which can burden network bandwidth and raise privacy risks. We present a loss-based alternative using distributed mutual learning. Instead of transmitting weights,…

Machine Learning · Computer Science 2025-03-11 Yash Gupta

Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Junhong Liu , Yuan Zhang , Tao Huang , Wenchao Xu , Renyu Yang

In the context of recent deep clustering studies, discriminative models dominate the literature and report the most competitive performances. These models learn a deep discriminative neural network classifier in which the labels are latent.…

Machine Learning · Computer Science 2019-12-17 Mohammed Jabi , Marco Pedersoli , Amar Mitiche , Ismail Ben Ayed

Deep Metric Learning (DML) aims to learn embedding functions that map semantically similar inputs to proximate points in a metric space while separating dissimilar ones. Existing methods, such as pairwise losses, are hindered by complex…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Pedro Silva , Guilherme A. L. Silva , Pablo Coelho , Vander Freitas , Gladston Moreira , David Menotii , Eduardo Luz

We study the fundamental and timely problem of learning long sequences in autoregressive modeling and next-token prediction under model misspecification, measured by the joint Kullback--Leibler (KL) divergence. Our goal is to characterize…

Machine Learning · Computer Science 2026-05-13 Yunbei Xu , Yuzhe Yuan , Ruohan Zhan

Neural models, with their ability to provide novel representations, have shown promising results in prediction tasks in healthcare. However, patient demographics, medical technology, and quality of care change over time. This often leads to…

Machine Learning · Computer Science 2022-12-02 Miguel Rios , Ameen Abu-Hanna

Variational Inference approximates an unnormalized distribution via the minimization of Kullback-Leibler (KL) divergence. Although this divergence is efficient for computation and has been widely used in applications, it suffers from some…

Machine Learning · Statistics 2022-07-28 Mingxuan Yi , Song Liu

Designing experiments that systematically gather data from complex physical systems is central to accelerating scientific discovery. While Bayesian experimental design (BED) provides a principled, information-based framework that integrates…

Machine Learning · Computer Science 2026-01-26 Huchen Yang , Xinghao Dong , Jin-Long Wu