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/zhanglab-deepneurocoglab/integrating-curricula-with-replays

공식 코드

Integrating Curricula with Replays: Its Effects on Continual Learning

https://github.com/zhen-tan-dmml/gfcil

공식 코드

Graph Few-shot Class-incremental Learning

https://github.com/zhengyuan-xie/eccv24_nest

공식 코드

Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation

https://github.com/zhenyutang2023/data_selection

공식 코드

Exploring Data Redundancy in Real-world Image Classification through Data Selection

https://github.com/zhepeiw/cssl_sound

공식 코드

Learning Representations for New Sound Classes With Continual Self-Supervised Learning

https://github.com/zhihelu/ending_iss

공식 코드

Evolving Knowledge Mining for Class Incremental Segmentation

https://github.com/zhilingyan/medical-sam-bench

공식 코드

SAMed-2: Selective Memory Enhanced Medical Segment Anything Model

https://github.com/zhixunlee/llm4gcl

공식 코드

Can LLMs Alleviate Catastrophic Forgetting in Graph Continual Learning? A Systematic Study

https://github.com/zhongwanjun/proqa

공식 코드

ProQA: Structural Prompt-based Pre-training for Unified Question Answering

https://github.com/zhoudw-zdw/MM21-Coil

공식 코드

Co-Transport for Class-Incremental Learning

https://github.com/zhoudw-zdw/PROOF

공식 코드

Learning without Forgetting for Vision-Language Models

https://github.com/zhoudw-zdw/TPAMI-Limit

공식 코드

Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks

https://github.com/zhoudw-zdw/cil_survey

공식 코드

A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

https://github.com/zhoudw-zdw/cvpr22-fact

공식 코드

Forward Compatible Few-Shot Class-Incremental Learning

https://github.com/zhoudw-zdw/revisitingcil

공식 코드

Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need

https://github.com/zhoujiahuan1991/aaai2025-caprompt

공식 코드

CAPrompt: Cyclic Prompt Aggregation for Pre-Trained Model Based Class Incremental Learning

https://github.com/zhu-gl-ux/adapter

공식 코드

Adaptive Prototype Replay for Class Incremental Semantic Segmentation

https://github.com/zhuang-li/cl_nsp

공식 코드

Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers

https://github.com/zhukaii/SPPR

공식 코드

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

https://github.com/zhwhu/mist

공식 코드

Beyond Freezing: Sparse Tuning Enhances Plasticity in Continual Learning with Pre-Trained Models

https://github.com/zinyy/treelora

공식 코드

TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree

https://github.com/zixuanke/lifelongsentclass

공식 코드

Continual Learning with Knowledge Transfer for Sentiment Classification

https://github.com/zixuanke/pycontinual

공식 코드

Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning

https://github.com/zizhao-hu/bvae

공식 코드

Encoding Binary Concepts in the Latent Space of Generative Models for Enhancing Data Representation

https://github.com/zj-jayzhang/Federated-Class-Continual-Learning

공식 코드

TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation

https://github.com/zju-vipa/meat-til

공식 코드

Meta-attention for ViT-backed Continual Learning

https://github.com/zjunlp/ContinueMKGC

공식 코드

Continual Multimodal Knowledge Graph Construction

https://github.com/zkzhang98/coinseg

공식 코드

CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation

https://github.com/zkzhang98/microseg

공식 코드

Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation

https://github.com/zoilsen/clom

공식 코드

Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation

https://github.com/zoilsen/comp-fscil

공식 코드

Compositional Few-Shot Class-Incremental Learning

https://github.com/zongrenzou/hjpde4sciml

공식 코드

Leveraging Multi-time Hamilton-Jacobi PDEs for Certain Scientific Machine Learning Problems

https://github.com/zongrenzou/timehjpde4sciml

공식 코드

Leveraging Hamilton-Jacobi PDEs with time-dependent Hamiltonians for continual scientific machine learning

https://github.com/zouxianghong/LifelongPR

공식 코드

LifelongPR: Lifelong knowledge fusion for point cloud place recognition based on replay and prompt learning

https://github.com/zqiao11/tscil

공식 코드

Class-incremental Learning for Time Series: Benchmark and Evaluation

https://github.com/zugexiaodui/vptinnsforcl

공식 코드

Visual Prompt Tuning in Null Space for Continual Learning

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