Copertina

Distribution-Level Memory Recall for Continual Learning: Preserving Knowledge and Avoiding Confusion

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cheng, Shaoxu, Geng, Kanglei, He, Chiyuan, Qiu, Zihuan, Xu, Linfeng, Qiu, Heqian, Wang, Lanxiao, Wu, Qingbo, Meng, Fanman, Li, Hongliang
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Continual Learning with Vision-Language Models via Semantic-Geometry Preservation
di: He, Chiyuan, et al.
Pubblicazione: (2026)

DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition
di: He, Chiyuan, et al.
Pubblicazione: (2025)

MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
di: Qiu, Zihuan, et al.
Pubblicazione: (2025)

Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus Adaptation
di: Shi, Zhaofeng, et al.
Pubblicazione: (2025)

Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation
di: Shi, Zhaofeng, et al.
Pubblicazione: (2024)

Few-Shot Continual Learning for Activity Recognition in Classroom Surveillance Images
di: Qian, Yilei, et al.
Pubblicazione: (2024)

Attention-disentangled Uniform Orthogonal Feature Space Optimization for Few-shot Object Detection
di: Zhao, Taijin, et al.
Pubblicazione: (2025)

Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency
di: Shi, Zhaofeng, et al.
Pubblicazione: (2026)

SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion
di: Li, Xiang, et al.
Pubblicazione: (2026)

Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning
di: Xu, Linfeng, et al.
Pubblicazione: (2023)

Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion
di: Chen, Yukun, et al.
Pubblicazione: (2025)

Closing the Oracle Gap: Increment Vector Transformation for Class Incremental Learning
di: Qiu, Zihuan, et al.
Pubblicazione: (2025)

Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity
di: Qiu, Zihuan, et al.
Pubblicazione: (2025)

ARIC: An Activity Recognition Dataset in Classroom Surveillance Images
di: Xu, Linfeng, et al.
Pubblicazione: (2024)

GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection
di: Mei, Hefei, et al.
Pubblicazione: (2023)

Region Prompt Tuning: Fine-grained Scene Text Detection Utilizing Region Text Prompt
di: Lin, Xingtao, et al.
Pubblicazione: (2024)

Cross-modal Cognitive Consensus guided Audio-Visual Segmentation
di: Shi, Zhaofeng, et al.
Pubblicazione: (2023)

MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning
di: Xiong, Huiyu, et al.
Pubblicazione: (2024)

Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection
di: Gao, Xiangyu, et al.
Pubblicazione: (2025)

FireRescue: A UAV-Based Dataset and Enhanced YOLO Model for Object Detection in Fire Rescue Scenes
di: Xu, Qingyu, et al.
Pubblicazione: (2025)

EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World
di: Qiu, Heqian, et al.
Pubblicazione: (2025)

Challenges and Trends in Egocentric Vision: A Survey
di: Li, Xiang, et al.
Pubblicazione: (2025)

No Re-Train, More Gain: Upgrading Backbones with Diffusion model for Pixel-Wise and Weakly-Supervised Few-Shot Segmentation
di: Chen, Shuai, et al.
Pubblicazione: (2024)

CMaP-SAM: Contraction Mapping Prior for SAM-driven Few-shot Segmentation
di: Chen, Shuai, et al.
Pubblicazione: (2025)

CMP: A Composable Meta Prompt for SAM-Based Cross-Domain Few-Shot Segmentation
di: Chen, Shuai, et al.
Pubblicazione: (2025)

DFR: A Decompose-Fuse-Reconstruct Framework for Multi-Modal Few-Shot Segmentation
di: Chen, Shuai, et al.
Pubblicazione: (2025)

Your Demands Deserve More Bits: Referring Semantic Image Compression at Ultra-low Bitrate
di: Wu, Chenhao, et al.
Pubblicazione: (2025)

On the Adversarial Robustness of Learning-based Image Compression Against Rate-Distortion Attacks
di: Wu, Chenhao, et al.
Pubblicazione: (2024)

Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning
di: Jiao, Jian, et al.
Pubblicazione: (2024)

Computational, Label, and Data Efficiency in Deep Learning for Sparse 3D Data
di: Li, Lanxiao
Pubblicazione: (2024)

PACE: Pretrained Audio Continual Learning
di: Li, Chang, et al.
Pubblicazione: (2026)

Facilitating NSFW Text Detection in Open-Domain Dialogue Systems via Knowledge Distillation
di: Qiu, Huachuan, et al.
Pubblicazione: (2023)

Gift Givers Over Avoid Sending Used Gifts
di: Tian Qiu, et al.
Pubblicazione: (2025)

Facilitating Pornographic Text Detection for Open-Domain Dialogue Systems via Knowledge Distillation of Large Language Models
di: Qiu, Huachuan, et al.
Pubblicazione: (2024)

TangZihuan/Cox-MK-file: Cox-MK-file
di: TangZihuan
Pubblicazione: (2026)

Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models
di: Zheng, Junhao, et al.
Pubblicazione: (2023)

AniArtAvatar: Animatable 3D Art Avatar from a Single Image
di: Li, Shaoxu
Pubblicazione: (2024)

Reflect then Learn: Active Prompting for Information Extraction Guided by Introspective Confusion
di: Zhao, Dong, et al.
Pubblicazione: (2025)

Privacy-Preserving Sequential Recommendation with Collaborative Confusion
di: Wang, Wei, et al.
Pubblicazione: (2024)

Task-Core Memory Management and Consolidation for Long-term Continual Learning
di: Huai, Tianyu, et al.
Pubblicazione: (2025)