English
Related papers

Related papers: Contrastive Distillation on Intermediate Represent…

200 papers

Knowledge Distillation (KD) has been considered as a key solution in model compression and acceleration in recent years. In KD, a small student model is generally trained from a large teacher model by minimizing the divergence between the…

Machine Learning · Computer Science 2021-11-16 Raed Alharbi , Minh N. Vu , My T. Thai

The enhancement of mathematical capabilities in large language models (LLMs) fosters new developments in mathematics education within primary and secondary schools, particularly as they relate to intelligent tutoring systems. However, LLMs…

Computation and Language · Computer Science 2025-07-08 Zhenquan Shen , Xinguo Yu , Xiaotian Cheng , Rao Peng , Hao Ming

Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained…

Information Retrieval · Computer Science 2022-08-23 Xinyu Ma , Ruqing Zhang , Jiafeng Guo , Yixing Fan , Xueqi Cheng

Knowledge distillation is a potential solution for model compression. The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one. Most previous…

Computer Vision and Pattern Recognition · Computer Science 2017-10-24 Chong Wang , Xipeng Lan , Yangang Zhang

We present an approach to ranking with dense representations that applies knowledge distillation to improve the recently proposed late-interaction ColBERT model. Specifically, we distill the knowledge from ColBERT's expressive MaxSim…

Information Retrieval · Computer Science 2020-10-23 Sheng-Chieh Lin , Jheng-Hong Yang , Jimmy Lin

Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data. However, these models are commonly pretrained…

Computer Vision and Pattern Recognition · Computer Science 2023-12-20 Yuang Liu , Jing Wang , Qiang Zhou , Fan Wang , Jun Wang , Wei Zhang

Knowledge distillation (KD) is an effective model compression technique where a compact student network is taught to mimic the behavior of a complex and highly trained teacher network. In contrast, Mutual Learning (ML) provides an…

Computer Vision and Pattern Recognition · Computer Science 2021-10-25 Usma Niyaz , Deepti R. Bathula

Previous logits-based Knowledge Distillation (KD) have utilized predictions about multiple categories within each sample (i.e., class predictions) and have employed Kullback-Leibler (KL) divergence to reduce the discrepancy between the…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Gyeongdo Ham , Seonghak Kim , Suin Lee , Jae-Hyeok Lee , Daeshik Kim

Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily…

Machine Learning · Computer Science 2019-04-22 Xiao Jin , Baoyun Peng , Yichao Wu , Yu Liu , Jiaheng Liu , Ding Liang , Junjie Yan , Xiaolin Hu

Language model compression through knowledge distillation has emerged as a promising approach for deploying large language models in resource-constrained environments. However, existing methods often struggle to maintain performance when…

Computation and Language · Computer Science 2025-02-26 Joshua Sakthivel Raju , Sanjay S , Jaskaran Singh Walia , Srinivas Raghav , Vukosi Marivate

Knowledge distillation is an effective way to transfer knowledge from a strong teacher to an efficient student model. Ideally, we expect the better the teacher is, the better the student. However, this expectation does not always come true.…

Information Retrieval · Computer Science 2023-06-27 Zhenghao Lin , Yeyun Gong , Xiao Liu , Hang Zhang , Chen Lin , Anlei Dong , Jian Jiao , Jingwen Lu , Daxin Jiang , Rangan Majumder , Nan Duan

The significant computational demands of large language models have increased interest in distilling reasoning abilities into smaller models via Chain-of-Thought (CoT) distillation. Current CoT distillation methods mainly focus on…

Computation and Language · Computer Science 2026-04-20 Yao Chen , Jiawei Sheng , Wenyuan Zhang , Tingwen Liu

Intermediate layer knowledge distillation (KD) can improve the standard KD technique (which only targets the output of teacher and student models) especially over large pre-trained language models. However, intermediate layer distillation…

Computation and Language · Computer Science 2021-10-05 Md Akmal Haidar , Nithin Anchuri , Mehdi Rezagholizadeh , Abbas Ghaddar , Philippe Langlais , Pascal Poupart

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Jiabao Wang , Yuming Chen , Zhaohui Zheng , Xiang Li , Ming-Ming Cheng , Qibin Hou

Contrastive Language-Image Pre-training (CLIP) has become a promising language-supervised visual pre-training framework. This paper aims to distill small CLIP models supervised by a large teacher CLIP model. We propose several distillation…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Chuanguang Yang , Zhulin An , Libo Huang , Junyu Bi , Xinqiang Yu , Han Yang , Boyu Diao , Yongjun Xu

Recent research on knowledge distillation has increasingly focused on logit distillation because of its simplicity, effectiveness, and versatility in model compression. In this paper, we introduce Refined Logit Distillation (RLD) to address…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Wujie Sun , Defang Chen , Siwei Lyu , Genlang Chen , Chun Chen , Can Wang

Knowledge distillation is commonly employed to compress neural networks, reducing the inference costs and memory footprint. In the scenario of homogenous architecture, feature-based methods have been widely validated for their…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Hongjun Wu , Li Xiao , Xingkuo Zhang , Yining Miao

Knowledge distillation (KD) is one of the most potent ways for model compression. The key idea is to transfer the knowledge from a deep teacher model (T) to a shallower student (S). However, existing methods suffer from performance…

Machine Learning · Computer Science 2020-02-24 Mengya Gao , Yujun Shen , Quanquan Li , Chen Change Loy

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…

Computation and Language · Computer Science 2020-05-11 Xing Wu , Yibing Liu , Xiangyang Zhou , Dianhai Yu

Representation knowledge distillation aims at transferring rich information from one model to another. Common approaches for representation distillation mainly focus on the direct minimization of distance metrics between the models'…

Computer Vision and Pattern Recognition · Computer Science 2022-04-06 Emanuel Ben-Baruch , Matan Karklinsky , Yossi Biton , Avi Ben-Cohen , Hussam Lawen , Nadav Zamir