Copertina

Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Fangwen, Cheng, Lechao, Tang, Shengeng, Zhu, Xiaofeng, Fang, Chaowei, Zhang, Dingwen, Wang, Meng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Calibrating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation
di: Cheng, Lechao, et al.
Pubblicazione: (2023)

Revisiting the Power of Prompt for Visual Tuning
di: Wang, Yuzhu, et al.
Pubblicazione: (2024)

Knowledge Swapping via Learning and Unlearning
di: Xing, Mingyu, et al.
Pubblicazione: (2025)

Modality Alignment Meets Federated Broadcasting
di: Ma, Yuting, et al.
Pubblicazione: (2024)

Towards Fine-Grained Emotion Understanding via Skeleton-Based Micro-Gesture Recognition
di: Xu, Hao, et al.
Pubblicazione: (2025)

Shaping a Stabilized Video by Mitigating Unintended Changes for Concept-Augmented Video Editing
di: Guo, Mingce, et al.
Pubblicazione: (2024)

Motion is the Choreographer: Learning Latent Pose Dynamics for Seamless Sign Language Generation
di: He, Jiayi, et al.
Pubblicazione: (2025)

Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
di: Zheng, Bowen, et al.
Pubblicazione: (2025)

IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation
di: Yu, Xiao, et al.
Pubblicazione: (2025)

Dataset Distillers Are Good Label Denoisers In the Wild
di: Cheng, Lechao, et al.
Pubblicazione: (2024)

Text-Driven Diffusion Model for Sign Language Production
di: He, Jiayi, et al.
Pubblicazione: (2025)

Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning
di: Yu, Fei, et al.
Pubblicazione: (2025)

Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation
di: Tang, Shengeng, et al.
Pubblicazione: (2024)

CanonSLR: Canonical-View Guided Multi-View Continuous Sign Language Recognition
di: Wang, Xu, et al.
Pubblicazione: (2026)

SignAligner: Harmonizing Complementary Pose Modalities for Coherent Sign Language Generation
di: Wang, Xu, et al.
Pubblicazione: (2025)

Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline
di: Li, Haiyang, et al.
Pubblicazione: (2025)

Efficient Vision Language Model Fine-tuning for Text-based Person Anomaly Search
di: He, Jiayi, et al.
Pubblicazione: (2025)

Dual-domain Adaptation Networks for Realistic Image Super-resolution
di: Fang, Chaowei, et al.
Pubblicazione: (2025)

StgcDiff: Spatial-Temporal Graph Condition Diffusion for Sign Language Transition Generation
di: He, Jiashu, et al.
Pubblicazione: (2025)

Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning
di: Park, Min-Yeong, et al.
Pubblicazione: (2024)

SplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition
di: Li, Jiahui, et al.
Pubblicazione: (2025)

Adaptive Prototype Replay for Class Incremental Semantic Segmentation
di: Zhu, Guilin, et al.
Pubblicazione: (2024)

DiffClass: Diffusion-Based Class Incremental Learning
di: Meng, Zichong, et al.
Pubblicazione: (2024)

PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental Learning
di: Qin, Yongchun, et al.
Pubblicazione: (2024)

Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
di: Yang, Ying, et al.
Pubblicazione: (2024)

Text2Lip: Progressive Lip-Synced Talking Face Generation from Text via Viseme-Guided Rendering
di: Wang, Xu, et al.
Pubblicazione: (2025)

PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning
di: Guo, Haiyang, et al.
Pubblicazione: (2024)

Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
di: Liu, Xialei, et al.
Pubblicazione: (2022)

OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL
di: Shen, Jinjie, et al.
Pubblicazione: (2026)

Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detection
di: Guo, Jiabao, et al.
Pubblicazione: (2025)

Class-wise Balancing Data Replay for Federated Class-Incremental Learning
di: Qi, Zhuang, et al.
Pubblicazione: (2025)

Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation
di: Xu, Wenbo, et al.
Pubblicazione: (2024)

Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement
di: Wu, Ruitao, et al.
Pubblicazione: (2025)

Towards Non-Exemplar Semi-Supervised Class-Incremental Learning
di: Liu, Wenzhuo, et al.
Pubblicazione: (2024)

Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation
di: Zhang, Dingwen, et al.
Pubblicazione: (2024)

Semantic-Aligned Learning with Collaborative Refinement for Unsupervised VI-ReID
di: Cheng, De, et al.
Pubblicazione: (2025)

Singular Value Fine-tuning for Few-Shot Class-Incremental Learning
di: Wang, Zhiwu, et al.
Pubblicazione: (2025)

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

EntityCLIP: Entity-Centric Image-Text Matching via Multimodal Attentive Contrastive Learning
di: Wang, Yaxiong, et al.
Pubblicazione: (2024)

TaE: Task-aware Expandable Representation for Long Tail Class Incremental Learning
di: Li, Linjie, et al.
Pubblicazione: (2024)