English
Related papers

Related papers: Inherit with Distillation and Evolve with Contrast…

200 papers

We investigate improving the retrieval effectiveness of embedding models through the lens of corpus-specific fine-tuning. Prior work has shown that fine-tuning with queries generated using a dataset's retrieval corpus can boost retrieval…

Information Retrieval · Computer Science 2025-05-27 Manveer Singh Tamber , Suleman Kazi , Vivek Sourabh , Jimmy Lin

In this work, we present DEcoupLEd Distillation To Erase (DELETE), a general and strong unlearning method for any class-centric tasks. To derive this, we first propose a theoretical framework to analyze the general form of unlearning loss…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Yu Zhou , Dian Zheng , Qijie Mo , Renjie Lu , Kun-Yu Lin , Wei-Shi Zheng

Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data. Due to time consumption, storage burden and privacy of old data, it is…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Dongbao Yang , Yu Zhou , Dayan Wu , Can Ma , Fei Yang , Weiping Wang

Compressing vision-language models for on-device deployment is increasingly important in clinical settings, but knowledge distillation (KD) degrades sharply when the teacher-student capacity gap spans an order of magnitude or more. We argue…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Numan Saeed , Asif Hanif , Fadillah Adamsyah Maani , Hussain Alasmawi , Mohammad Yaqub

Semi-supervised medical image segmentation has attracted much attention in recent years because of the high cost of medical image annotations. In this paper, we propose a novel Inherent Consistent Learning (ICL) method, aims to learn robust…

Computer Vision and Pattern Recognition · Computer Science 2023-04-19 Ye Zhu , Jie Yang , Si-Qi Liu , Ruimao Zhang

Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one, under the constraints of having limited system size and computational…

Computer Vision and Pattern Recognition · Computer Science 2023-01-16 Sheng-Feng Yu , Wei-Chen Chiu

The field of Continual Learning (CL) has inspired numerous researchers over the years, leading to increasingly advanced countermeasures to the issue of catastrophic forgetting. Most studies have focused on the single-class scenario, where…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Martin Menabue , Emanuele Frascaroli , Matteo Boschini , Lorenzo Bonicelli , Angelo Porrello , Simone Calderara

Instance-incremental learning (IIL) focuses on learning continually with data of the same classes. Compared to class-incremental learning (CIL), the IIL is seldom explored because IIL suffers less from catastrophic forgetting (CF). However,…

Machine Learning · Computer Science 2024-06-06 Qiang Nie , Weifu Fu , Yuhuan Lin , Jialin Li , Yifeng Zhou , Yong Liu , Lei Zhu , Chengjie Wang

Continual learning aims to accumulate knowledge over a data stream while mitigating catastrophic forgetting. In Non-exemplar Class Incremental Learning (NECIL), forgetting arises during incremental optimization because old classes are…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Haori Lu , Xusheng Cao , Linlan Huang , Enguang Wang , Fei Yang , Xialei Liu

The field of continual deep learning is an emerging field and a lot of progress has been made. However, concurrently most of the approaches are only tested on the task of image classification, which is not relevant in the field of…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Tobias Kalb , Masoud Roschani , Miriam Ruf , Jürgen Beyerer

General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on task boundaries during both training and testing stages. We…

Computer Vision and Pattern Recognition · Computer Science 2023-01-02 Zhong Ji , Jin Li , Qiang Wang , Zhongfei Zhang

Despite their success for semantic segmentation, convolutional neural networks are ill-equipped for incremental learning, \ie, adapting the original segmentation model as new classes are available but the initial training data is not…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Zilong Huang , Wentian Hao , Xinggang Wang , Mingyuan Tao , Jianqiang Huang , Wenyu Liu , Xian-Sheng Hua

Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step~(DSS), a novel method utilizing chain-of-thought~(CoT)…

Computation and Language · Computer Science 2024-06-11 Xin Chen , Hanxian Huang , Yanjun Gao , Yi Wang , Jishen Zhao , Ke Ding

This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD). The focus of this method is on capturing and transferring knowledge between the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-01 Ayoub Karine , Thibault Napoléon , Maher Jridi

This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in federated learning. Existing FCCL works suffer from various limitations, such as requiring…

Machine Learning · Computer Science 2023-08-21 Jie Zhang , Chen Chen , Weiming Zhuang , Lingjuan Lv

The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Xiuwei Chen , Xiaobin Chang

Large Language models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities, where a LLM makes predictions for a given test input together with a few input-output pairs (demonstrations). Nevertheless, the inclusion of…

Computation and Language · Computer Science 2024-03-13 Yichuan Li , Xiyao Ma , Sixing Lu , Kyumin Lee , Xiaohu Liu , Chenlei Guo

Diffusion models excel at generative modeling (e.g., text-to-image) but sampling requires multiple denoising network passes, limiting practicality. Efforts such as progressive distillation or consistency distillation have shown promise by…

Machine Learning · Computer Science 2025-04-01 Risheek Garrepalli , Shweta Mahajan , Munawar Hayat , Fatih Porikli

Although deep learning performs really well in a wide variety of tasks, it still suffers from catastrophic forgetting -- the tendency of neural networks to forget previously learned information upon learning new tasks where previous data is…

Computer Vision and Pattern Recognition · Computer Science 2020-02-04 Ankur Singh

Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made…

Computer Vision and Pattern Recognition · Computer Science 2021-11-25 Umberto Michieli , Pietro Zanuttigh