English
Related papers

Related papers: Stable Distillation: Regularizing Continued Pre-tr…

200 papers

Knowledge distillation (KD) shows a bright promise as a powerful regularization strategy to boost generalization ability by leveraging learned sample-level soft targets. Yet, employing a complex pre-trained teacher network or an ensemble of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-06 Yiqing Shen , Liwu Xu , Yuzhe Yang , Yaqian Li , Yandong Guo

Adversarial training is a widely adopted strategy to bolster the robustness of neural network models against adversarial attacks. This paper revisits the fundamental assumptions underlying image classification and suggests that representing…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Erh-Chung Chen , Che-Rung Lee

Transformer encoder with connectionist temporal classification (CTC) framework is widely used for automatic speech recognition (ASR). However, knowledge distillation (KD) for ASR displays a problem of disagreement between teacher-student…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-13 Eungbeom Kim , Hantae Kim , Kyogu Lee

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persistent challenge. In this paper, we propose a novel self-supervised speaker verification approach, Self-Distillation…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-30 Yafeng Chen , Siqi Zheng , Hui Wang , Luyao Cheng , Qian Chen , Chong Deng , Shiliang Zhang , Wen Wang

Much of the focus in the area of knowledge distillation has been on distilling knowledge from a larger teacher network to a smaller student network. However, there has been little research on how the concept of distillation can be leveraged…

Neural and Evolutionary Computing · Computer Science 2019-01-29 Zhong Qiu Lin , Alexander Wong

Self-supervised learning (SSL) techniques have achieved remarkable results in various speech processing tasks. Nonetheless, a significant challenge remains in reducing the reliance on vast amounts of speech data for pre-training. This paper…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-05 Po-chun Hsu , Ali Elkahky , Wei-Ning Hsu , Yossi Adi , Tu Anh Nguyen , Jade Copet , Emmanuel Dupoux , Hung-yi Lee , Abdelrahman Mohamed

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Zelong Zeng , Fan Yang , Zheng Wang , Shin'ichi Satoh

Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters.…

Computation and Language · Computer Science 2023-02-13 Haoran Xu , Jean Maillard , Vedanuj Goswami

Distillation is a method to transfer knowledge from one model to another and often achieves higher accuracy with the same capacity. In this paper, we aim to provide a theoretical understanding on what mainly helps with the distillation. Our…

Machine Learning · Statistics 2019-10-04 Bin Dong , Jikai Hou , Yiping Lu , Zhihua Zhang

In this paper, we propose a novel self-distillation method for fake speech detection (FSD), which can significantly improve the performance of FSD without increasing the model complexity. For FSD, some fine-grained information is very…

Sound · Computer Science 2023-03-03 Jun Xue , Cunhang Fan , Jiangyan Yi , Chenglong Wang , Zhengqi Wen , Dan Zhang , Zhao Lv

Existing knowledge distillation methods mostly focus on distillation of teacher's prediction and intermediate activation. However, the structured representation, which arguably is one of the most critical ingredients of deep models, is…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Jing Yang , Xiatian Zhu , Adrian Bulat , Brais Martinez , Georgios Tzimiropoulos

Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a 'pretext task' that does not require ground-truth labels/annotation. This…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Sotirios Konstantakos , Jorgen Cani , Ioannis Mademlis , Despina Ioanna Chalkiadaki , Yuki M. Asano , Efstratios Gavves , Georgios Th. Papadopoulos

We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in…

Computation and Language · Computer Science 2023-12-13 Ibtihel Amara , Vinija Jain , Aman Chadha

This paper proposes a self-regularised minimum latency training (SR-MLT) method for streaming Transformer-based automatic speech recognition (ASR) systems. In previous works, latency was optimised by truncating the online attention weights…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-25 Mohan Li , Rama Doddipatla , Catalin Zorila

Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience.…

While self-supervised representation learning (SSL) has received widespread attention from the community, recent research argue that its performance will suffer a cliff fall when the model size decreases. The current method mainly relies on…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Yuting Gao , Jia-Xin Zhuang , Shaohui Lin , Hao Cheng , Xing Sun , Ke Li , Chunhua Shen

Surgical tool detection in minimally invasive surgery is an essential part of computer-assisted interventions. Current approaches are mostly based on supervised methods which require large fully labeled data to train supervised models and…

Computer Vision and Pattern Recognition · Computer Science 2022-12-26 Mansoor Ali , Gilberto Ochoa-Ruiz , Sharib Ali

On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the…

Machine Learning · Computer Science 2026-05-07 Xin Yu , Liuchen Liao , Yiwen Zhang , Yingchen Yu , Lingzhou Xue , Qinzhen Guo

Recently, non-autoregressive (NAT) models predict outputs in parallel, achieving substantial improvements in generation speed compared to autoregressive (AT) models. While performing worse on raw data, most NAT models are trained as student…

Computation and Language · Computer Science 2021-12-23 Jiaxin Guo , Minghan Wang , Daimeng Wei , Hengchao Shang , Yuxia Wang , Zongyao Li , Zhengzhe Yu , Zhanglin Wu , Yimeng Chen , Chang Su , Min Zhang , Lizhi Lei , shimin tao , Hao Yang

Despite the outstanding success of self-supervised pretraining methods for video representation learning, they generalise poorly when the unlabeled dataset for pretraining is small or the domain difference between unlabelled data in source…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Amirhossein Dadashzadeh , Alan Whone , Majid Mirmehdi