English
Related papers

Related papers: DisCo: Distilled Student Models Co-training for Se…

200 papers

Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…

Computer Vision and Pattern Recognition · Computer Science 2019-01-15 Shitao Tang , Litong Feng , Wenqi Shao , Zhanghui Kuang , Wei Zhang , Yimin Chen

Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Zakaria Laskar , Juho Kannala

Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and…

Machine Learning · Computer Science 2023-02-01 Tatiana Likhomanenko , Ronan Collobert , Navdeep Jaitly , Samy Bengio

Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing…

Computer Vision and Pattern Recognition · Computer Science 2023-06-12 Seanie Lee , Minki Kang , Juho Lee , Sung Ju Hwang , Kenji Kawaguchi

Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. However, the class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation.…

Computer Vision and Pattern Recognition · Computer Science 2025-01-13 Yin Wang , Zixuan Wang , Hao Lu , Zhen Qin , Hailiang Zhao , Guanjie Cheng , Ge Su , Li Kuang , Mengchu Zhou , Shuiguang Deng

This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…

Computation and Language · Computer Science 2024-12-30 Shuo Wang , Chihang Wang , Jia Gao , Zhen Qi , Hongye Zheng , Xiaoxuan Liao

The deep complex convolution recurrent network (DCCRN) achieves excellent speech enhancement performance by utilizing the audio spectrum's complex features. However, it has a large number of model parameters. We propose a smaller model,…

Sound · Computer Science 2024-08-09 Runduo Han , Weiming Xu , Zihan Zhang , Mingshuai Liu , Lei Xie

The current success of deep neural networks (DNNs) in an increasingly broad range of tasks involving artificial intelligence strongly depends on the quality and quantity of labeled training data. In general, the scarcity of labeled data,…

Computation and Language · Computer Science 2018-11-21 Shun Kiyono , Jun Suzuki , Kentaro Inui

Leveraging shared learning through Massively Multilingual Models, state-of-the-art machine translation models are often able to adapt to the paucity of data for low-resource languages. However, this performance comes at the cost of…

Computation and Language · Computer Science 2022-11-10 Harshita Diddee , Sandipan Dandapat , Monojit Choudhury , Tanuja Ganu , Kalika Bali

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

Knowledge distillation is an effective approach to transferring knowledge from a teacher neural network to a student target network for satisfying the low-memory and fast running requirements in practice use. Whilst being able to create…

Computer Vision and Pattern Recognition · Computer Science 2018-11-20 Xu Lan , Xiatian Zhu , Shaogang Gong

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the…

Computation and Language · Computer Science 2026-01-16 Lechen Zhang , Yunxiang Zhang , Wei Hu , Lu Wang

Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency. We believe the insufficient utilization of training signals should be responsible. To alleviate this…

Computer Vision and Pattern Recognition · Computer Science 2023-01-03 Xin Ma , Chang Liu , Chunyu Xie , Long Ye , Yafeng Deng , Xiangyang Ji

Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to directly train small language models (SLMs) to emerge long…

Computation and Language · Computer Science 2025-06-19 Zhaoyang Wang , Jinqi Jiang , Tian Qiu , Hui Liu , Xianfeng Tang , Huaxiu Yao

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges…

Computation and Language · Computer Science 2020-04-07 Wenhui Wang , Furu Wei , Li Dong , Hangbo Bao , Nan Yang , Ming Zhou

Masked image modeling (MIM) is a highly effective self-supervised learning (SSL) approach to extract useful feature representations from unannotated data. Predominantly used random masking methods make SSL less effective for medical images…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Jue Jiang , Aneesh Rangnekar , Harini Veeraraghavan

Large-scale self-supervised pre-trained speech encoders outperform conventional approaches in speech recognition and translation tasks. Due to the high cost of developing these large models, building new encoders for new tasks and deploying…

Computation and Language · Computer Science 2023-12-29 Heng-Jui Chang , Ning Dong , Ruslan Mavlyutov , Sravya Popuri , Yu-An Chung

Self-supervised learning (SSL) is seen as a very promising approach with high performance for several speech downstream tasks. Since the parameters of SSL models are generally so large that training and inference require a lot of memory and…

Computation and Language · Computer Science 2022-09-02 Takanori Ashihara , Takafumi Moriya , Kohei Matsuura , Tomohiro Tanaka

Data-free knowledge distillation~(DFKD) is an effective manner to solve model compression and transmission restrictions while retaining privacy protection, which has attracted extensive attention in recent years. Currently, the majority of…

Machine Learning · Computer Science 2025-10-07 Renrong Shao , Wei Zhang , Jun wang

Knowledge distillation is a technique to enhance the generalization ability of a student model by exploiting outputs from a teacher model. Recently, feature-map based variants explore knowledge transfer between manually assigned…

Computer Vision and Pattern Recognition · Computer Science 2021-08-31 Defang Chen , Jian-Ping Mei , Yuan Zhang , Can Wang , Yan Feng , Chun Chen