English
Related papers

Related papers: Hybrid Memory Replay: Blending Real and Distilled …

200 papers

Dataset distillation aims to minimize the time and memory needed for training deep networks on large datasets, by creating a small set of synthetic images that has a similar generalization performance to that of the full dataset. However,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Xuxi Chen , Yu Yang , Zhangyang Wang , Baharan Mirzasoleiman

Feature Distillation (FD) strategies are proven to be effective in mitigating Catastrophic Forgetting (CF) seen in Class Incremental Learning (CIL). However, current FD approaches enforce strict alignment of feature magnitudes and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 S Balasubramanian , Yedu Krishna P , Talasu Sai Sriram , M Sai Subramaniam , Manepalli Pranav Phanindra Sai , Darshan Gera

Reinforcement Learning (RL) has shown promise for aligning Large Language Models (LLMs) to follow instructions with various constraints. Despite the encouraging results, RL improvement inevitably relies on sampling successful, high-quality…

Artificial Intelligence · Computer Science 2025-12-30 Kongcheng Zhang , Qi Yao , Shunyu Liu , Wenjian Zhang , Min Cen , Yang Zhou , Wenkai Fang , Yiru Zhao , Baisheng Lai , Mingli Song

Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that…

Machine Learning · Computer Science 2024-03-27 Huiping Zhuang , Run He , Kai Tong , Ziqian Zeng , Cen Chen , Zhiping Lin

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation…

Computation and Language · Computer Science 2020-12-15 Fei Yuan , Linjun Shou , Jian Pei , Wutao Lin , Ming Gong , Yan Fu , Daxin Jiang

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Machine Learning · Computer Science 2025-12-30 Amirhossein Tighkhorshid , Zahra Dehghanian , Gholamali Aminian , Chengchun Shi , Hamid R. Rabiee

Replay-based methods in class-incremental learning (CIL) have attained remarkable success. Despite their effectiveness, the inherent memory restriction results in saving a limited number of exemplars with poor diversity. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Ruxiao Duan , Jieneng Chen , Adam Kortylewski , Alan Yuille , Yaoyao Liu

Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to prevent forgetting previously learned classes include…

Machine Learning · Computer Science 2024-07-02 Elif Ceren Gok Yildirim , Murat Onur Yildirim , Mert Kilickaya , Joaquin Vanschoren

Active learning can be defined as iterations of data labeling, model training, and data acquisition, until sufficient labels are acquired. A traditional view of data acquisition is that, through iterations, knowledge from human labels and…

Machine Learning · Computer Science 2022-01-28 Beong-woo Kwak , Youngwook Kim , Yu Jin Kim , Seung-won Hwang , Jinyoung Yeo

This paper addresses the challenge of incremental learning in growing graphs with increasingly complex tasks. The goal is to continuously train a graph model to handle new tasks while retaining proficiency in previous tasks via memory…

Machine Learning · Computer Science 2025-03-04 Ziyue Qiao , Junren Xiao , Qingqiang Sun , Meng Xiao , Xiao Luo , Hui Xiong

Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond…

Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Zakaria Laskar , Juho Kannala

State-space models (SSMs) offer efficient sequence modeling but lag behind Transformers on benchmarks that require in-context retrieval. Prior work links this gap to a small set of attention heads, termed Gather-and-Aggregate (G&A), which…

Machine Learning · Computer Science 2026-02-13 Aviv Bick , Eric P. Xing , Albert Gu

Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure,…

Machine Learning · Computer Science 2023-11-21 Tiantian Zhang , Kevin Zehua Shen , Zichuan Lin , Bo Yuan , Xueqian Wang , Xiu Li , Deheng Ye

In this paper, we address the problem of distillation-based class-incremental learning with a single head. A central theme of this task is to learn new classes that arrive in sequential phases over time while keeping the model's capability…

Computer Vision and Pattern Recognition · Computer Science 2021-01-25 Cheng-Hsun Lei , Yi-Hsin Chen , Wen-Hsiao Peng , Wei-Chen Chiu

Deep neural networks perform remarkably well in close-world scenarios. However, novel classes emerged continually in real applications, making it necessary to learn incrementally. Class-incremental learning (CIL) aims to gradually recognize…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Wenzhuo Liu , Fei Zhu , Cheng-Lin Liu

Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot…

Machine Learning · Computer Science 2021-11-23 Zixuan Ni , Siliang Tang , Yueting Zhuang

Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…

Computer Vision and Pattern Recognition · Computer Science 2018-09-05 Francisco M. Castro , Manuel J. Marín-Jiménez , Nicolás Guil , Cordelia Schmid , Karteek Alahari

Existing imitation learning (IL) methods such as inverse reinforcement learning (IRL) usually have a double-loop training process, alternating between learning a reward function and a policy and tend to suffer long training time and high…

Machine Learning · Computer Science 2022-06-13 Siwei Chen , Xiao Ma , Zhongwen Xu

Large Language models (LLMs) are achieving state-of-the-art performance in many different downstream tasks. However, the increasing urgency of data privacy puts pressure on practitioners to train LLMs with Differential Privacy (DP) on…

Machine Learning · Computer Science 2025-12-17 James Flemings , Murali Annavaram