paper-with-me

Papers Exemplar-Free

“Exemplar-Free” 태그가 달린 논문 72편 · 필터 해제

Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning

2025-07-05 · Stanisław Pawlak, Bartłomiej Twardowski, Tomasz Trzciński, Joost Van de Weijer

Our research addresses the overlooked security concerns related to data poisoning in continual learning (CL). Data poisoning - the intentional manipulation of training data to affect the predictions of machine learning m…

Continual LearningData PoisoningExemplar-Free

DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic

2025-06-26 · Munish Monga, Vishal Chudasama, Pankaj Wasnik, Biplab Banerjee

Real-world object detection systems, such as those in autonomous driving and surveillance, must continuously learn new object categories and simultaneously adapt to changing environmental conditions. Existing approaches,…

Autonomous DrivingAvgClass-Incremental Object DetectionExemplar-Free+5

L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning

2025-06-01 · Xiang Zhang, Run He, Jiao Chen, Di Fang 외

Class-incremental learning (CIL) enables models to learn new classes continually without forgetting previously acquired knowledge. Multi-label CIL (MLCIL) extends CIL to a real-world scenario where each sample may belong…

class-incremental learningClass Incremental LearningExemplar-FreeIncremental Learning+2

Exemplar-Free Continual Learning for State Space Models

2025-05-24 · Isaac Ning Lee, Leila Mahmoodi, Trung Le, Mehrtash Harandi

State-Space Models (SSMs) excel at capturing long-range dependencies with structured recurrence, making them well-suited for sequence modeling. However, their evolving internal states pose challenges in adapting them und…

Continual LearningExemplar-FreeState Space Models

Listen, Analyze, and Adapt to Learn New Attacks: An Exemplar-Free Class Incremental Learning Method for Audio Deepfake Source Tracing

2025-05-20 · Yang Xiao, Rohan Kumar Das

As deepfake speech becomes common and hard to detect, it is vital to trace its source. Recent work on audio deepfake source tracing (ST) aims to find the origins of synthetic or manipulated speech. However, ST models mus…

class-incremental learningClass Incremental LearningContinual LearningDeepFake Detection+3

StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning

2025-05-20 · Huaijie Wang, De Cheng, Guozhang Li, Zhipeng Xu 외

Video Class-Incremental Learning (VCIL) seeks to develop models that continuously learn new action categories over time without forgetting previously acquired knowledge. Unlike traditional Class-Incremental Learning (CIL…

class-incremental learningClass Incremental LearningExemplar-FreeIncremental Learning+1

AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting

2025-05-17 · Yang Xiao, Tianyi Peng, Rohan Kumar Das, Yuchen Hu 외

Keyword spotting (KWS) offers a vital mechanism to identify spoken commands in voice-enabled systems, where user demands often shift, requiring models to learn new keywords continually over time. However, a major problem…

class-incremental learningClass Incremental LearningContinual LearningExemplar-Free+3

Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification

2025-04-21 · Shiben Liu, Huijie Fan, Qiang Wang, Baojie Fan 외

Lifelong Person Re-identification (LReID) suffers from a key challenge in preserving old knowledge while adapting to new information. The existing solutions include rehearsal-based and rehearsal-free methods to address t…

Exemplar-FreeKnowledge DistillationLifelong learningMixture-of-Experts+4

Audio-Visual Class-Incremental Learning for Fish Feeding intensity Assessment in Aquaculture

2025-04-21 · Meng Cui, Xianghu Yue, Xinyuan Qian, Jinzheng Zhao 외

Fish Feeding Intensity Assessment (FFIA) is crucial in industrial aquaculture management. Recent multi-modal approaches have shown promise in improving FFIA robustness and efficiency. However, these methods face signific…

Benchmarkingclass-incremental learningClass Incremental LearningExemplar-Free+1

Boosting the Class-Incremental Learning in 3D Point Clouds via Zero-Collection-Cost Basic Shape Pre-Training

2025-04-11 · Chao Qi, Jianqin Yin, Meng Chen, Yingchun Niu 외

Existing class-incremental learning methods in 3D point clouds rely on exemplars (samples of former classes) to resist the catastrophic forgetting of models, and exemplar-free settings will greatly degrade the performanc…

3D geometryclass-incremental learningClass Incremental LearningExemplar-Free+1

LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning

2025-03-23 · CVPR 2025 1 · Xuan Liu, Xiaobin Chang

In continual learning (CL), catastrophic forgetting often arises due to feature drift. This challenge is particularly prominent in the exemplar-free continual learning (EFCL) setting, where samples from previous tasks ca…

Continual LearningExemplar-Freeparameter-efficient fine-tuningTriplet

EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning

2025-03-13 · Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost Van de Weijer 외

Exemplar-Free Class Incremental Learning (EFCIL) aims to learn from a sequence of tasks without having access to previous task data. In this paper, we consider the challenging Cold Start scenario in which insufficient da…

class-incremental learningClass Incremental LearningExemplar-FreeIncremental Learning

Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning

2025-03-07 · Run He, Di Fang, Yicheng Xu, Yawen Cui 외

Exemplar-Free Class-Incremental Learning (EFCIL) aims to sequentially learn from distinct categories without retaining exemplars but easily suffers from catastrophic forgetting of learned knowledge. While existing EFCIL …

class-incremental learningClass Incremental LearningExemplar-FreeIncremental Learning+1

Incremental Learning with Repetition via Pseudo-Feature Projection

2025-02-27 · Benedikt Tscheschner, Eduardo Veas, Marc Masana

Incremental Learning scenarios do not always represent real-world inference use-cases, which tend to have less strict task boundaries, and exhibit repetition of common classes and concepts in their continual data stream.…

Exemplar-FreeIncremental Learning

ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking

2025-02-18 · Rong Li, Tao Deng, Siwei Feng, MingJie Sun 외

WiFi-based human activity recognition (HAR) holds significant application potential across various fields. To handle dynamic environments where new activities are continuously introduced, WiFi-based HAR systems must adap…

Activity Recognitionclass-incremental learningClass Incremental LearningExemplar-Free+2

On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning

2025-01-26 · Tianqi Wang, Jingcai Guo, Depeng Li, Zhi Chen

Exemplar-free class incremental learning (EF-CIL) is a nontrivial task that requires continuously enriching model capability with new classes while maintaining previously learned knowledge without storing and replaying a…

class-incremental learningClass Incremental LearningExemplar-FreeIncremental Learning

PAL: Prompting Analytic Learning with Missing Modality for Multi-Modal Class-Incremental Learning

2025-01-16 · Xianghu Yue, Yiming Chen, Xueyi Zhang, Xiaoxue Gao 외

Multi-modal class-incremental learning (MMCIL) seeks to leverage multi-modal data, such as audio-visual and image-text pairs, thereby enabling models to learn continuously across a sequence of tasks while mitigating forg…

class-incremental learningClass Incremental LearningExemplar-FreeIncremental Learning

CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning

2025-01-13 · Tieyuan Chen, Huabin Liu, Chern Hong Lim, John See 외

Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task beco…

class-incremental learningClass Incremental LearningContinual LearningExemplar-Free+2

Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning

2024-12-24 · CVPR 2025 1 · Takuma Fukuda, Hiroshi Kera, Kazuhiko Kawamoto

We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability. While existing methods trad…

class-incremental learningClass Incremental LearningExemplar-FreeIncremental Learning

DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification

2024-12-12 · Kunlun Xu, Chenghao Jiang, Peixi Xiong, Yuxin Peng 외

Lifelong person re-identification (LReID) is an important but challenging task that suffers from catastrophic forgetting due to significant domain gaps between training steps. Existing LReID approaches typically rely on …

Exemplar-FreeKnowledge DistillationPerson Re-IdentificationStyle Transfer
1–20 / 72 다음 →