English
Related papers

Related papers: SPREAD: Subspace Representation Distillation for L…

200 papers

Backpropagation (BP), while foundational to deep learning, imposes two critical scalability bottlenecks: update locking, where network modules remain idle until the entire backward pass completes, and high memory consumption due to storing…

Machine Learning · Computer Science 2025-10-07 Chenhao Ye , Ming Tang

In recent years, deep neural networks have achieved remarkable accuracy in computer vision tasks. With inference time being a crucial factor, particularly in dense prediction tasks such as semantic segmentation, knowledge distillation has…

Computer Vision and Pattern Recognition · Computer Science 2023-08-09 Amir M. Mansourian , Rozhan Ahmadi , Shohreh Kasaei

Knowledge Distillation (KD) is a popular technique to transfer knowledge from a teacher model or ensemble to a student model. Its success is generally attributed to the privileged information on similarities/consistency between the class…

Machine Learning · Computer Science 2021-07-02 Zhen Huang , Xu Shen , Jun Xing , Tongliang Liu , Xinmei Tian , Houqiang Li , Bing Deng , Jianqiang Huang , Xian-Sheng Hua

Score Distillation Sampling (SDS) has been pivotal for leveraging pre-trained diffusion models in downstream tasks such as inverse problems, but it faces two major challenges: $(i)$ mode collapse and $(ii)$ latent space inversion, which…

Machine Learning · Computer Science 2024-10-15 Nicolas Zilberstein , Morteza Mardani , Santiago Segarra

Feature-based knowledge distillation aims to transfer intermediate representations from a teacher LLM model to a student. Existing approaches typically rely on direct feature matching or learned projections, implicitly treating…

Computation and Language · Computer Science 2026-02-11 Khouloud Saadi , Di Wang

Continual learning aims to provide intelligent agents that are capable of learning continually a sequence of tasks, building on previously learned knowledge. A key challenge in this learning paradigm is catastrophically forgetting…

Machine Learning · Computer Science 2021-01-18 Ghada Sokar , Decebal Constantin Mocanu , Mykola Pechenizkiy

Due to the success of large-scale visual-language pretraining (VLP) models and the widespread use of image-text retrieval in industry areas, it is now critically necessary to reduce the model size and streamline their mobile-device…

Computer Vision and Pattern Recognition · Computer Science 2024-04-03 Youbo Lei , Feifei He , Chen Chen , Yingbin Mo , Si Jia Li , Defeng Xie , Haonan Lu

Knowledge distillation transfers knowledge from a high capacity teacher to a compact student using a mixture of hard and soft losses. On imbalanced data, a fixed weighting between hard and soft losses becomes brittle the learning process.…

Machine Learning · Computer Science 2026-05-20 Anh B. H. Nguyen , Ba Tho Phan , Viet Cuong Ta

Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter…

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

Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the relation of data…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Muzhou Yu , Sia Huat Tan , Kailu Wu , Runpei Dong , Linfeng Zhang , Kaisheng Ma

The gap in representations between image and video makes Image-to-Video Re-identification (I2V Re-ID) challenging, and recent works formulate this problem as a knowledge distillation (KD) process. In this paper, we propose a mutual…

Computer Vision and Pattern Recognition · Computer Science 2022-01-25 Pichao Wang , Fan Wang , Hao Li

Deep learning is increasingly being applied in safety-critical domains. For these scenarios it is important to know the level of uncertainty in a model's prediction to ensure appropriate decisions are made by the system. Deep ensembles are…

Machine Learning · Computer Science 2022-03-17 Yassir Fathullah , Mark J. F. Gales

Multimodal Dataset Distillation (MDD) seeks to condense large-scale image-text datasets into compact surrogates while retaining their effectiveness for cross-modal learning. Despite recent progress, existing MDD approaches often suffer from…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Xin Zhang , Ziruo Zhang , Jiawei Du , Zuozhu Liu , Joey Tianyi Zhou

Knowledge distillation (KD) compresses the network capacity by transferring knowledge from a large (teacher) network to a smaller one (student). It has been mainstream that the teacher directly transfers knowledge to the student with its…

The downstream accuracy of self-supervised methods is tightly linked to the proxy task solved during training and the quality of the gradients extracted from it. Richer and more meaningful gradients updates are key to allow self-supervised…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Tim Lebailly , Tinne Tuytelaars

Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Cuipeng Wang , Haipeng Wang

In real-world applications, Federated Learning (FL) meets two challenges: (1) scalability, especially when applied to massive IoT networks; and (2) how to be robust against an environment with heterogeneous data. Realizing the first…

Machine Learning · Computer Science 2022-10-03 Minh-Duong Nguyen , Quoc-Viet Pham , Dinh Thai Hoang , Long Tran-Thanh , Diep N. Nguyen , Won-Joo Hwang

Self-supervised learning (SSL) has revolutionized audio representations, yet models often remain domain-specific, focusing on either speech or non-speech tasks. In this work, we present Universal Speech and Audio Distillation (USAD), a…

Sound · Computer Science 2025-08-19 Heng-Jui Chang , Saurabhchand Bhati , James Glass , Alexander H. Liu

Knowledge Distillation (KD) has emerged as a powerful technique for model compression, enabling lightweight student networks to benefit from the performance of redundant teacher networks. However, the inherent capacity gap often limits the…

Machine Learning · Computer Science 2026-02-12 Yiyun Zhou , Jingwei Shi , Mingjing Xu , Zhonghua Jiang , Jingyuan Chen

Catastrophic forgetting has been a major challenge in continual learning, where the model needs to learn new tasks with limited or no access to data from previously seen tasks. To tackle this challenge, methods based on knowledge…

Machine Learning · Computer Science 2023-06-29 Qiao Gu , Dongsub Shim , Florian Shkurti