English
Related papers

Related papers: Stratified Knowledge-Density Super-Network for Sca…

200 papers

Knowledge distillation (KD) is a powerful model compression technique broadly used in practical deep learning applications. It is focused on training a small student network to mimic a larger teacher network. While it is widely known that…

Machine Learning · Computer Science 2023-09-21 Valeriy Berezovskiy , Nikita Morozov

Knowledge distillation (KD) has traditionally relied on a static teacher-student framework, where a large, well-trained teacher transfers knowledge to a single student model. However, these approaches often suffer from knowledge…

Computer Vision and Pattern Recognition · Computer Science 2025-11-05 Md. Abdur Rahman , Mohaimenul Azam Khan Raiaan , Sami Azam , Asif Karim , Jemima Beissbarth , Amanda Leach

In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Xu Zheng , Yunhao Luo , Pengyuan Zhou , Lin Wang

In Natural Language Processing (NLP), Transformers have already revolutionized the field by utilizing an attention-based encoder-decoder model. Recently, some pioneering works have employed Transformer-like architectures in Computer Vision…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Gousia Habib , Tausifa Jan Saleem , Brejesh Lall

Knowledge Distillation (KD) is a predominant approach for BERT compression. Previous KD-based methods focus on designing extra alignment losses for the student model to mimic the behavior of the teacher model. These methods transfer the…

Computation and Language · Computer Science 2024-03-21 Taiqiang Wu , Cheng Hou , Shanshan Lao , Jiayi Li , Ngai Wong , Zhe Zhao , Yujiu Yang

Sparsification-based pruning has been an important category in model compression. Existing methods commonly set sparsity-inducing penalty terms to suppress the importance of dropped weights, which is regarded as the suppressed…

Computer Vision and Pattern Recognition · Computer Science 2024-03-12 Shengji Tang , Weihao Lin , Hancheng Ye , Peng Ye , Chong Yu , Baopu Li , Tao Chen

Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. However, existing works applying KD to QAT require tedious hyper-parameter tuning to…

Machine Learning · Computer Science 2024-03-19 Kaiqi Zhao , Ming Zhao

Vision Transformers (ViTs) are built on the assumption of treating image patches as ``visual tokens" and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Ryan Grainger , Thomas Paniagua , Xi Song , Naresh Cuntoor , Mun Wai Lee , Tianfu Wu

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 aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…

Machine Learning · Computer Science 2023-05-26 Shiya Luo , Defang Chen , Can Wang

Knowledge distillation(KD) aims to improve the performance of a student network by mimicing the knowledge from a powerful teacher network. Existing methods focus on studying what knowledge should be transferred and treat all samples equally…

Computer Vision and Pattern Recognition · Computer Science 2020-08-05 Youcai Zhang , Zhonghao Lan , Yuchen Dai , Fangao Zeng , Yan Bai , Jie Chang , Yichen Wei

While transfer learning is an effective strategy, it often overlooks the opportunity to leverage knowledge from numerous available models online. Addressing this multi-source transfer learning problem is a promising path to boost…

Machine Learning · Computer Science 2026-04-24 Marcin Osial , Bartosz Wójcik , Bartosz Zieliński , Sebastian Cygert

Unstructured pruning remains a powerful strategy for compressing deep neural networks, yet it often demands iterative train-prune-retrain cycles, resulting in significant computational overhead. To address this challenge, we introduce a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 Md. Samiul Alim , Sharjil Khan , Amrijit Biswas , Fuad Rahman , Shafin Rahman , Nabeel Mohammed

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Jialiang Tang , Shuo Chen , Gang Niu , Masashi Sugiyama , Chen Gong

This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation. Directly employing previous distillation approaches yields inferior results due to the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Yuenan Hou , Xinge Zhu , Yuexin Ma , Chen Change Loy , Yikang Li

Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Mengcheng Lan , Min Meng , Jun Yu , Jigang Wu

In this work, we consider transferring the structure information from large networks to compact ones for dense prediction tasks in computer vision. Previous knowledge distillation strategies used for dense prediction tasks often directly…

Computer Vision and Pattern Recognition · Computer Science 2020-06-16 Yifan Liu , Changyong Shun , Jingdong Wang , Chunhua Shen

Pre-trained models have become the preferred backbone due to the increasing complexity of model parameters. However, traditional pre-trained models often face deployment challenges due to their fixed sizes, and are prone to negative…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Yucheng Xie , Fu Feng , Ruixiao Shi , Jing Wang , Yong Rui , Xin Geng

Knowledge Distillation (KD) has been one of the most popu-lar methods to learn a compact model. However, it still suffers from highdemand in time and computational resources caused by sequential train-ing pipeline. Furthermore, the soft…

Computer Vision and Pattern Recognition · Computer Science 2020-08-28 Benlin Liu , Yongming Rao , Jiwen Lu , Jie Zhou , Cho-jui Hsieh

Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet their prediction process remains difficult to interpret because information is propagated through complex interactions across layers and attention heads.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Sehyeong Jo , Gangjae Jang , Haesol Park
‹ Prev 1 2 3 10 Next ›