English
Related papers

Related papers: FEDS: Feature and Entropy-Based Distillation Strat…

200 papers

Current approaches for restoration of degraded images face a trade-off: high-performance models are slow for practical use, while fast models produce poor results. Knowledge distillation transfers teacher knowledge to students, but existing…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Shourya Verma , Mengbo Wang , Nadia Atallah Lanman , Ananth Grama

Sampling from pretrained diffusion and flow-matching models typically requires many forward passes to generate diverse and high-fidelity images. Existing distillation methods often rely on multiple auxiliary networks, carefully designed…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Yuan Zhang , Chenyi Li , Guoqing Ma , Jiajun Zha , Yuanming Yang , Bo Wang , Wei Tang , Wenbo Li , Haoyang Huang , Nan Duan

With the rapid development of computer vision, Vision Transformers (ViTs) offer the tantalising prospect of unified information processing across visual and textual domains due to the lack of inherent inductive biases in ViTs. ViTs require…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Gousia Habib , Tausifa Jan Saleem , Ishfaq Ahmad Malik , Brejesh Lall

Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing…

Image and Video Processing · Electrical Eng. & Systems 2024-12-17 Han Li , Shaohui Li , Wenrui Dai , Chenglin Li , Junni Zou , Hongkai Xiong

Recent advances in distilling expensive diffusion models into efficient few-step generators show significant promise. However, these methods typically demand substantial computational resources and extended training periods, limiting…

Computer Vision and Pattern Recognition · Computer Science 2026-04-27 Jincheng Ying , Yitao Chen , Li Wenlin , Minghui Xu , Yinhao Xiao

Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Lu Yu , Vacit Oguz Yazici , Xialei Liu , Joost van de Weijer , Yongmei Cheng , Arnau Ramisa

Recent advances in learned image compression (LIC) have achieved remarkable performance improvements over traditional codecs. Notably, the MLIC series-LICs equipped with multi-reference entropy models-have substantially surpassed…

Image and Video Processing · Electrical Eng. & Systems 2026-02-26 Wei Jiang , Yongqi Zhai , Jiayu Yang , Feng Gao , Ronggang Wang

Learned Image Compression (LIC) models have achieved superior rate-distortion performance than traditional codecs. Existing LIC models use CNN, Transformer, or Mixed CNN-Transformer as basic blocks. However, limited by the shifted window…

Image and Video Processing · Electrical Eng. & Systems 2025-02-11 Heng Xu , Bowen Hai , Yushun Tang , Zhihai He

There has been much interest in deploying deep learning algorithms on low-powered devices, including smartphones, drones, and medical sensors. However, full-scale deep neural networks are often too resource-intensive in terms of energy and…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Yoshitomo Matsubara , Ruihan Yang , Marco Levorato , Stephan Mandt

Federated Learning (FL) is a promising technique for the collaborative training of deep neural networks across multiple devices while preserving data privacy. Despite its potential benefits, FL is hindered by excessive communication costs…

Machine Learning · Computer Science 2024-02-27 Vasileios Tsouvalas , Aaqib Saeed , Tanir Ozcelebi , Nirvana Meratnia

Recently, deep learning technology has been successfully applied in the field of image compression, leading to superior rate-distortion performance. It is crucial to design an effective and efficient entropy model to estimate the…

Image and Video Processing · Electrical Eng. & Systems 2024-07-03 Yongqiang Wang , Haisheng Fu , Qi Cao , Shang Wang , Zhenjiao Chen , Feng Liang

Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted. For the sake of practicality, a thorough…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Dailan He , Ziming Yang , Weikun Peng , Rui Ma , Hongwei Qin , Yan Wang

Knowledge Distillation (KD) has emerged as a promising approach for transferring knowledge from a larger, more complex teacher model to a smaller student model. Traditionally, KD involves training the student to mimic the teacher's output…

Machine Learning · Computer Science 2024-10-03 Noel Loo , Fotis Iliopoulos , Wei Hu , Erik Vee

Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present. The entropy model plays a key role in learned…

Computer Vision and Pattern Recognition · Computer Science 2025-05-16 Jingbo Lu , Leheng Zhang , Xingyu Zhou , Mu Li , Wen Li , Shuhang Gu

Recently, the compression and deployment of powerful deep neural networks (DNNs) on resource-limited edge devices to provide intelligent services have become attractive tasks. Although knowledge distillation (KD) is a feasible solution for…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Zhiwei Hao , Yong Luo , Zhi Wang , Han Hu , Jianping An

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

Artificial Intelligence · Computer Science 2023-01-31 Chaochen Gao , Xing Wu , Peng Wang , Jue Wang , Liangjun Zang , Zhongyuan Wang , Songlin Hu

Layer-wise distillation is a powerful tool to compress large models (i.e. teacher models) into small ones (i.e., student models). The student distills knowledge from the teacher by mimicking the hidden representations of the teacher at…

Computation and Language · Computer Science 2023-06-07 Chen Liang , Simiao Zuo , Qingru Zhang , Pengcheng He , Weizhu Chen , Tuo Zhao

Dynamic graph representation learning strategies are based on different neural architectures to capture the graph evolution over time. However, the underlying neural architectures require a large amount of parameters to train and suffer…

Machine Learning · Computer Science 2020-11-12 Stefanos Antaris , Dimitrios Rafailidis

Reconstructing high-fidelity flow fields from low-fidelity observations is a central problem in scientific machine learning, yet recent diffusion and flow-matching models typically rely on iterative sampling, making them costly for…

Machine Learning · Computer Science 2026-05-08 Sicheng Ma , Tianyue Yang , Xiuzhe Wu , Xiao Xue

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