Papers with Code 아카이브

Continual Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 5
평가표: 33
보존된 평가 기록: 133

Continual Learning (also known as Incremental Learning, Life-long Learning) is a concept to learn a model for a large number of tasks sequentially without forgetting knowledge obtained from the preceding tasks, where the data in the old tasks are not available anymore during training new ones.
If not mentioned, the benchmarks here are Task-CL, where task-id is provided on validation.

Source:
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
Three scenarios for continual learning
Lifelong Machine Learning
Continual lifelong learning with neural networks: A review

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/jasoncodemaker/ctvr

공식 코드

StableFusion: Continual Video Retrieval via Frame Adaptation

https://github.com/jayatejak/gvalign

공식 코드

Robust Feature Learning and Global Variance-Driven Classifier Alignment for Long-Tail Class Incremental Learning

https://github.com/jayatejak/s3c

공식 코드

S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning

https://github.com/jc043/cpl

공식 코드

Continual Predictive Learning from Videos

https://github.com/jedrzejkozal/weight-interpolation-cl

공식 코드

Continual Learning with Weight Interpolation

https://github.com/jerry2398/pi-gnn

공식 코드

Continual Learning on Dynamic Graphs via Parameter Isolation

https://github.com/jessemelpolio/anytimecl

공식 코드

Anytime Continual Learning for Open Vocabulary Classification

https://github.com/jessemelpolio/treeprobe

공식 코드

Continual Learning in Open-vocabulary Classification with Complementary Memory Systems

https://github.com/jiahuadong/hfc

공식 코드

Heterogeneous Forgetting Compensation for Class-Incremental Learning

https://github.com/jiahuadong/lga

공식 코드

No One Left Behind: Real-World Federated Class-Incremental Learning

https://github.com/jiangpenghe/cl-lora

공식 코드

CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning

https://github.com/jianzhangcs/r-dfcil

공식 코드

R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning

https://github.com/jiaolifengmi/vq-prompt

공식 코드

Vector Quantization Prompting for Continual Learning

https://github.com/jiazuoyu/moe-adapters4cl

공식 코드

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters

https://github.com/jiazuoyu/pathweave

공식 코드

LLMs Can Evolve Continually on Modality for X-Modal Reasoning

https://github.com/jieshibo/confit

공식 코드

Alleviating Representational Shift for Continual Fine-tuning

https://github.com/jihwankwak/ciss_partitioned

공식 코드

Towards Realistic Incremental Scenario in Class Incremental Semantic Segmentation

https://github.com/jinchaogjc/cit

공식 코드

CIT: Rethinking Class-incremental Semantic Segmentation with a Class Independent Transformation

https://github.com/jindeok/CF-KAN

공식 코드

CF-KAN: Kolmogorov-Arnold Network-based Collaborative Filtering to Mitigate Catastrophic Forgetting in Recommender Systems

https://github.com/jinghan1he/seekr

공식 코드

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models

https://github.com/jinglin-liang/dddr

공식 코드

Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning

https://github.com/jingruihou/clnir

공식 코드

Advancing continual lifelong learning in neural information retrieval: definition, dataset, framework, and empirical evaluation

https://github.com/jingwang18/silan

공식 코드

What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context

https://github.com/jinlab-imvr/feddah

공식 코드

Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for FCL

https://github.com/jinpeng0528/balconpas

공식 코드

Strike a Balance in Continual Panoptic Segmentation

https://github.com/jmdvinodjmd/HyperITE

공식 코드

A Brief Review of Hypernetworks in Deep Learning

https://github.com/joansj/hat

공식 코드

Overcoming catastrophic forgetting with hard attention to the task

https://github.com/jodie-kang/doublemixture

공식 코드

Double Mixture: Towards Continual Event Detection from Speech

https://github.com/joeljang/continual-knowledge-learning

공식 코드

Towards Continual Knowledge Learning of Language Models

https://github.com/joeljang/temporalwiki

공식 코드

TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models

https://github.com/joeljosephjin/La-MAML

공식 코드

Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning

https://github.com/joey-wang123/DRO-Task-free

공식 코드

Improving Task-free Continual Learning by Distributionally Robust Memory Evolution

https://github.com/joey-wang123/cl-refresh-learning

공식 코드

A Unified and General Framework for Continual Learning

https://github.com/johswald/learning_where_to_learn

공식 코드

Learning where to learn: Gradient sparsity in meta and continual learning

https://github.com/jojotenya/LAMOL

공식 코드

LAMOL: LAnguage MOdeling for Lifelong Language Learning

https://github.com/jon17591/multi-lingual-agents

공식 코드

Multi-lingual agents through multi-headed neural networks

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.