Papers with Code 아카이브
Class Incremental Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 6
- 보존된 평가 기록
- 14
Incremental learning of a sequence of tasks when the task-ID is not available at test time.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Learn by Reasoning: Analogical Weight Generation for Few-Shot Class-Incremental Learning
IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting
Continual learning via probabilistic exchangeable sequence modelling
Adaptive Weighted Parameter Fusion with CLIP for Class-Incremental Learning
Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
Feature Calibration enhanced Parameter Synthesis for CLIP-based Class-incremental Learning
Reducing Class-wise Confusion for Incremental Learning with Disentangled Manifolds
Technical Report for the 5th CLVision Challenge at CVPR: Addressing the Class-Incremental with Repetition using Unlabeled Data -- 4th Place Solution
Robust3D-CIL: Robust Class-Incremental Learning for 3D Perception
An experimental approach on Few Shot Class Incremental Learning
A New Benchmark for Few-Shot Class-Incremental Learning: Redefining the Upper Bound
Singular Value Fine-tuning for Few-Shot Class-Incremental Learning
Generative Binary Memory: Pseudo-Replay Class-Incremental Learning on Binarized Embeddings
EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning
External Knowledge Injection for CLIP-Based Class-Incremental Learning
Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networks
PTMs-TSCIL Pre-Trained Models Based Class-Incremental Learning
MultiCo3D: Multi-Label Voxel Contrast for One-Shot Incremental Segmentation of 3D Neuroimages
Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning
Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection
FSCIL-SEI: Few-Shot Class-Incremental Learning Approach for Specific Emitter Identification
Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
Class-Independent Increment: An Efficient Approach for Multi-label Class-Incremental Learning
Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping
Brain-inspired analogical mixture prototypes for few-shot class-incremental learning
Sculpting [CLS] Features for Pre-Trained Model-Based Class-Incremental Learning
ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking
Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning
Memory Is Not the Bottleneck: Cost-Efficient Continual Learning via Weight Space Consolidation
Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation
Leveraging Pre-Trained Models for Multimodal Class-Incremental Learning under Adaptive Fusion
Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning
Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting
On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.