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/sun-hailong/lamda-pilot

공식 코드

PILOT: A Pre-Trained Model-Based Continual Learning Toolbox

https://github.com/superallen13/CaT-CGL

공식 코드

CaT: Balanced Continual Graph Learning with Graph Condensation

https://github.com/superallen13/puma

공식 코드

PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensation

https://github.com/supersoob/carm

공식 코드

Carousel Memory: Rethinking the Design of Episodic Memory for Continual Learning

https://github.com/supritivijay/nerda-con

공식 코드

NERDA-Con: Extending NER models for Continual Learning -- Integrating Distinct Tasks and Updating Distribution Shifts

https://github.com/swagshaw/asc-cl

공식 코드

Continual Learning For On-Device Environmental Sound Classification

https://github.com/szc12153/cldyb

공식 코드

CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models

https://github.com/tachukao/ncl

공식 코드

Natural continual learning: success is a journey, not (just) a destination

https://github.com/tachyonicclock/surprisenet-cikm-23

공식 코드

Look At Me, No Replay! SurpriseNet: Anomaly Detection Inspired Class Incremental Learning

https://github.com/talreiss/PANDA

공식 코드

PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation

https://github.com/tamasham/napa-vq

공식 코드

NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual Learning

https://github.com/tambourine666/Covariance-Space-Regularize

공식 코드

Covariance-based Space Regularization for Few-shot Class Incremental Learning

https://github.com/tanmdl/scale

공식 코드

Scalable Adversarial Online Continual Learning

https://github.com/tdemin16/continual-layernorm-tuning

공식 코드

On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers

https://github.com/tdemin16/multi-lane

공식 코드

Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning

https://github.com/team-approx-bayes/BayesBiNN

공식 코드

Training Binary Neural Networks using the Bayesian Learning Rule

https://github.com/team-approx-bayes/dl-with-bayes

공식 코드

Practical Deep Learning with Bayesian Principles

https://github.com/tecsar-uncc/pheva

공식 코드

PHEVA: A Privacy-preserving Human-centric Video Anomaly Detection Dataset

https://github.com/tf63/acmap

공식 코드

Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning

https://github.com/tgeral68/continual_learning_of_long_topic

공식 코드

Continual Learning of Long Topic Sequences in Neural Information Retrieval

https://github.com/thomasjoshi/agents-never-forget

공식 코드

SWE-Bench-CL: Continual Learning for Coding Agents

https://github.com/thomasscialom/t0_continual_learning

공식 코드

Fine-tuned Language Models are Continual Learners

https://github.com/thousandbrainsproject/tbp.monty

공식 코드

The Thousand Brains Project: A New Paradigm for Sensorimotor Intelligence

https://github.com/thu-coai/cpt4dst

공식 코드

Continual Prompt Tuning for Dialog State Tracking

https://github.com/thu-ml/hide-prompt

공식 코드

Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality

https://github.com/thu-spmi/ppt2dst

공식 코드

Prompt Pool based Class-Incremental Continual Learning for Dialog State Tracking

https://github.com/thunderbeee/zscl

공식 코드

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

https://github.com/tianqi-py/agale

공식 코드

AGALE: A Graph-Aware Continual Learning Evaluation Framework

https://github.com/tiansongs/pl-fscil

공식 코드

PL-FSCIL: Harnessing the Power of Prompts for Few-Shot Class-Incremental Learning

https://github.com/timelyeventsbenchmark/tiebe

공식 코드

TiEBe: Tracking Language Model Recall of Notable Worldwide Events Through Time

https://github.com/timmhess/kaaff

공식 코드

Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting

https://github.com/timmhess/twocomplementaryperspectivescl

공식 코드

Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How

https://github.com/timrudner/S-FSVI

공식 코드

Continual Learning via Sequential Function-Space Variational Inference

https://github.com/tldoan/PCA-OGD

공식 코드

A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix

https://github.com/tldoan/clip-m3

공식 코드

A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets

https://github.com/tldoan/clip_m3

공식 코드

A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets

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