https://github.com/thunderbeee/zscl
공식 코드Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Incremental learning aims to develop artificially intelligent systems that can continuously learn to address new tasks from new data while preserving knowledge learned from previously learned tasks.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
Preliminary Study on Incremental Learning for Large Language Model-based Recommender Systems
PL-FSCIL: Harnessing the Power of Prompts for Few-Shot Class-Incremental Learning
Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
A Simple yet Brisk and Efficient Active Learning Platform for Text Classification
A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets
A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets
Text-Enhanced Data-free Approach for Federated Class-Incremental Learning
Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection
Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions
When Prompt-based Incremental Learning Does Not Meet Strong Pretraining
Few-shot Class-incremental Learning for 3D Point Cloud Objects
Incremental Learning of Structured Memory via Closed-Loop Transcription
CCSI: Continual Class-Specific Impression for Data-free Class Incremental Learning
An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control
CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation
Multi-stream Fusion for Class Incremental Learning in Pill Image Classification
Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning
Visual Memorability for Robotic Interestingness via Unsupervised Online Learning
HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration
Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent
Knowledge Restore and Transfer for Multi-label Class-Incremental Learning
WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration
Class-Incremental Exemplar Compression for Class-Incremental Learning
Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.