English
Related papers

Related papers: Refined Response Distillation for Class-Incrementa…

200 papers

As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation…

Computer Vision and Pattern Recognition · Computer Science 2023-02-13 Guang Yang , Yin Tang , Jun Li , Jianhua Xu , Xili Wan

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

Model extraction attacks (MEAs) on large language models (LLMs) have received increasing attention in recent research. However, existing attack methods typically adapt the extraction strategies originally developed for deep neural networks…

Cryptography and Security · Computer Science 2025-05-20 Zi Liang , Qingqing Ye , Yanyun Wang , Sen Zhang , Yaxin Xiao , Ronghua Li , Jianliang Xu , Haibo Hu

Adversarial training (AT) is considered the most effective defense against adversarial attacks. However, a recent study revealed that \(\ell_{\infty}\)-norm adversarial training (\(\ell_{\infty}\)-AT) will also induce unevenly distributed…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Junxi Chen , Junhao Dong , Xiaohua Xie , Jianhuang Lai

We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to…

Distribution matching distillation (DMD) facilitates few-step image generation by aligning a distilled student with a reference multi-step teacher. In practice, however, optimizing DMD can reduce sample diversity in few-step synthesis, and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Tianhe Wu , Ruibin Li , Lei Zhang , Kede Ma

Despite the remarkable progress in open-vocabulary object detection (OVD), a significant gap remains between the training and testing phases. During training, the RPN and RoI heads often misclassify unlabeled novel-category objects as…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yupeng Zhang , Ruize Han , Zhiwei Chen , Wei Feng , Liang Wan

The advent of scalable deep models and large datasets has improved the performance of Neural Machine Translation. Knowledge Distillation (KD) enhances efficiency by transferring knowledge from a teacher model to a more compact student…

Computation and Language · Computer Science 2024-03-26 Heegon Jin , Seonil Son , Jemin Park , Youngseok Kim , Hyungjong Noh , Yeonsoo Lee

Current knowledge distillation (KD) methods primarily focus on transferring various structured knowledge and designing corresponding optimization goals to encourage the student network to imitate the output of the teacher network. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Dong Liang , Yue Sun , Yun Du , Songcan Chen , Sheng-Jun Huang

Despite the success of deep learning models on instance segmentation, current methods still suffer from catastrophic forgetting in continual learning scenarios. In this paper, our contributions for continual instance segmentation are…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Mathieu Pagé-Fortin , Brahim Chaib-draa

Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. However, these approaches typically require tens or even hundreds of…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Xiao He , Huaao Tang , Zhijun Tu , Junchao Zhang , Kun Cheng , Hanting Chen , Yong Guo , Mingrui Zhu , Nannan Wang , Xinbo Gao , Jie Hu

Diverse input data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while a (training) dataset could be accurately designed to include a variety of…

Computer Vision and Pattern Recognition · Computer Science 2018-10-30 Nuno Garcia , Pietro Morerio , Vittorio Murino

Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradients (IG) as a data augmentation strategy. Our approach…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 David E. Hernandez , Jose Chang , Torbjörn E. M. Nordling

Continuous category discovery (CCD) aims to automatically discover novel categories in continuously arriving unlabeled data. This is a challenging problem considering that there is no number of categories and labels in the newly arrived…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Ruobing Jiang , Yang Liu , Haobing Liu , Yanwei Yu , Chunyang Wang

Diffusion models achieve state-of-the-art generative performance but are fundamentally bottlenecked by their slow, iterative sampling process. While diffusion distillation techniques enable high-fidelity, few-step generation, traditional…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Linqian Fan , Peiqin Sun , Tiancheng Wen , Shun Lu , Chengru Song

Knowledge distillation is an effective and hardware-friendly method, which plays a key role in lightweighting remote sensing object detection. However, existing distillation methods often encounter the issue of mixed features in remote…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Xiangyi Gao , Danpei Zhao , Bo Yuan , Wentao Li

Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2024-08-28 Jichuan Zhang , Wei Li , Shuang Cheng , Ya-Li Li , Shengjin Wang

Knowledge distillation (KD) has gained much attention due to its effectiveness in compressing large-scale pre-trained models. In typical KD methods, the small student model is trained to match the soft targets generated by the big teacher…

Machine Learning · Computer Science 2021-09-13 Yitao Liu , Tianxiang Sun , Xipeng Qiu , Xuanjing Huang

We address the problem of fine-tuning diffusion models for reward-guided generation in biomolecular design. While diffusion models have proven highly effective in modeling complex, high-dimensional data distributions, real-world…

Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Gang Li , Xiang Li , Yujie Wang , Shanshan Zhang , Yichao Wu , Ding Liang