English
Related papers

Related papers: Efficient Distillation of Classifier-Free Guidance…

200 papers

Recent approaches have shown promises distilling diffusion models into efficient one-step generators. Among them, Distribution Matching Distillation (DMD) produces one-step generators that match their teacher in distribution, without…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Tianwei Yin , Michaël Gharbi , Taesung Park , Richard Zhang , Eli Shechtman , Fredo Durand , William T. Freeman

Diffusion models have emerged as a pivotal advancement in generative models, setting new standards to the quality of the generated instances. In the current paper we aim to underscore a discrepancy between conventional training methods and…

Machine Learning · Computer Science 2023-11-03 Niket Patel , Luis Salamanca , Luis Barba

Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-conditional diffusion guidance methods, such as classifier…

Computer Vision and Pattern Recognition · Computer Science 2023-08-25 Susung Hong , Gyuseong Lee , Wooseok Jang , Seungryong Kim

Knowledge distillation has made remarkable achievements in model compression. However, most existing methods require the original training data, which is usually unavailable due to privacy and security issues. In this paper, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2022-08-15 Xinyi Yu , Ling Yan , Yang Yang , Libo Zhou , Linlin Ou

Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inherent redundancy in visual content to make training more affordable by training only on a subset…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Felix Krause , Stefan Andreas Baumann , Johannes Schusterbauer , Olga Grebenkova , Ming Gui , Vincent Tao Hu , Björn Ommer

Score Distillation Sampling (SDS) has made significant strides in distilling image-generative models for 3D generation. However, its maximum-likelihood-seeking behavior often leads to degraded visual quality and diversity, limiting its…

Computer Vision and Pattern Recognition · Computer Science 2025-01-10 Runjie Yan , Yinbo Chen , Xiaolong Wang

Diffusion models excel in image generation but are computational and resource-intensive due to their reliance on iterative Markov chain processes, leading to error accumulation and limiting the effectiveness of naive compression techniques.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Beomseok Ko , Hyeryung Jang

Graph neural networks (GNNs) have shown remarkable performance on diverse graph mining tasks. Although different GNNs can be unified as the same message passing framework, they learn complementary knowledge from the same graph. Knowledge…

Machine Learning · Computer Science 2023-04-06 Zhichun Guo , Chunhui Zhang , Yujie Fan , Yijun Tian , Chuxu Zhang , Nitesh Chawla

Recent advances in diffusion-based generative models have shown incredible promise for zero shot image-to-image translation and editing. Most of these approaches work by combining or replacing network-specific features used in the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Zeqi Gu , Ethan Yang , Abe Davis

Despite plentiful successes achieved by graph representation learning in various domains, the training of graph neural networks (GNNs) still remains tenaciously challenging due to the tremendous computational overhead needed for sizable…

Machine Learning · Computer Science 2025-05-28 Yurui Lai , Taiyan Zhang , Renchi Yang

In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in deep learning training tasks. CT-AGD is a general boosting procedure that accelerates…

Machine Learning · Computer Science 2026-05-18 Manuel Graca , L. Miguel Silveira , Arlindo Oliveira , Frank Liu

Adaptive densification is the engine of 3D Gaussian Splatting (3DGS). However, when transposed to the optimization-based Generative Distillation paradigm, this reconstruction-native mechanism reveals fundamental limitations, resulting in…

Machine Learning · Computer Science 2026-05-21 SeungJeh Chung , Geonho Park , Misong Kim , HyeongYeop Kang

Proper guidance strategies are essential to achieve high-quality generation results without retraining diffusion and flow-based text-to-image models. Existing guidance either requires specific training or strong inductive biases of…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Tiancheng Li , Weijian Luo , Zhiyang Chen , Liyuan Ma , Guo-Jun Qi

In this paper, we propose a new distillation method for extracting knowledge from Large Foundation Models (LFM) into lightweight models, introducing a novel supervision mode that does not require manually annotated data. While LFMs exhibit…

Computer Vision and Pattern Recognition · Computer Science 2024-08-23 Yijin Xu , Jialun Liu , Hualiang Wei , Wenhui Li

Knowledge Distillation is becoming one of the primary trends among neural network compression algorithms to improve the generalization performance of a smaller student model with guidance from a larger teacher model. This momentous rise in…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Sumanth Chennupati , Mohammad Mahdi Kamani , Zhongwei Cheng , Lin Chen

Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental…

Machine Learning · Computer Science 2026-03-24 Jing Liu , Zhenchao Ma , Han Yu , Bobo Ju , Wenliang Yang , Chengfang Li , Bo Hu , Liang Song

Classifier-Free Guidance (CFG) has recently emerged in text-to-image generation as a lightweight technique to encourage prompt-adherence in generations. In this work, we demonstrate that CFG can be used broadly as an inference-time…

Computation and Language · Computer Science 2023-07-03 Guillaume Sanchez , Honglu Fan , Alexander Spangher , Elad Levi , Pawan Sasanka Ammanamanchi , Stella Biderman

Data-free Knowledge Distillation (DFKD) is a method that constructs pseudo-samples using a generator without real data, and transfers knowledge from a teacher model to a student by enforcing the student to overcome dimensional differences…

Machine Learning · Computer Science 2025-04-03 Yuang Jia , Xiaojuan Shan , Jun Xia , Guancheng Wan , Yuchen Zhang , Wenke Huang , Mang Ye , Stan Z. Li

Instance-aware embeddings predicted by deep neural networks have revolutionized biomedical instance segmentation, but its resource requirements are substantial. Knowledge distillation offers a solution by transferring distilled knowledge…

Computer Vision and Pattern Recognition · Computer Science 2024-01-15 Xiaoyu Liu , Yueyi Zhang , Zhiwei Xiong , Wei Huang , Bo Hu , Xiaoyan Sun , Feng Wu

Machine learning force field (MLFF) has emerged as a powerful data-driven tool for atomistic simulations, enabling large-scale and complex atomic systems to be simulated with accuracy comparable to \textit{ab initio} methods. However, MLFFs…

Chemical Physics · Physics 2026-04-06 Ruiyang Chen , Qingyuan Zhang , Ji Chen