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/czjghost/afs

공식 코드

New Insights on Relieving Task-Recency Bias for Online Class Incremental Learning

https://github.com/dacaidi/lrfr

공식 코드

Learning a Low-Rank Feature Representation: Achieving Better Trade-Off between Stability and Plasticity in Continual Learning

https://github.com/dallepezze/adcl_scale

공식 코드

Continual Learning Approaches for Anomaly Detection

https://github.com/danielm1405/BinPlay

공식 코드

BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning

https://github.com/danielm1405/magmax

공식 코드

MagMax: Leveraging Model Merging for Seamless Continual Learning

https://github.com/danielm1405/sl-vs-ssl-cl

공식 코드

Revisiting Supervision for Continual Representation Learning

https://github.com/dannis97500/cp_prompt

공식 코드

CP-Prompt: Composition-Based Cross-modal Prompting for Domain-Incremental Continual Learning

https://github.com/danruod/fs-dgpm

공식 코드

Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning

https://github.com/daofeng-liu/cdd-r

공식 코드

Centroid Distance Distillation for Effective Rehearsal in Continual Learning

https://github.com/datadistillation/datadam

공식 코드

DataDAM: Efficient Dataset Distillation with Attention Matching

https://github.com/dawnliu35/fscil-asp

공식 코드

Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt

https://github.com/decisionintelligence/qcore

공식 코드

QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models -- Extended Version

https://github.com/deepfakeil/dfil

공식 코드

DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues

https://github.com/deeplearnxmu/ssr

공식 코드

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal

https://github.com/deepmind/deepmind-research

공식 코드

Continual Unsupervised Representation Learning

https://github.com/deepmind/deepmind-research/tree/master/gated_linear_networks

공식 코드

A Combinatorial Perspective on Transfer Learning

https://github.com/deepmind/dm_nevis

공식 코드

NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research

https://github.com/deepseek-ai/DeepEP

공식 코드

A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications

https://github.com/delchiaro/RATT

공식 코드

RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning

https://github.com/demonjianz/s2c

공식 코드

Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning

https://github.com/dentonjc/memory-sampling

공식 코드

Non-Uniform Memory Sampling in Experience Replay

https://github.com/dequino/spiking-compressed-continual-learning

공식 코드

Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks

https://github.com/dfki-av/awt-for-ciss

공식 코드

Attribution-aware Weight Transfer: A Warm-Start Initialization for Class-Incremental Semantic Segmentation

https://github.com/diadai/cfs

공식 코드

Open Continual Feature Selection via Granular-Ball Knowledge Transfer

https://github.com/dice-group/dice-embeddings

공식 코드

Hardware-agnostic Computation for Large-scale Knowledge Graph Embeddings

https://github.com/diningphil/continual_learning_for_graphs

공식 코드

Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification

https://github.com/dipamgoswami/adc

공식 코드

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning

https://github.com/dipamgoswami/fecam

공식 코드

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

https://github.com/dipamgoswami/fscil-calibration

공식 코드

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers

https://github.com/divyam3897/ucl

공식 코드

Representational Continuity for Unsupervised Continual Learning

https://github.com/djo1996/Bayesian_Continual_Learning_And_Forgetting

공식 코드

Bayesian continual learning and forgetting in neural networks

https://github.com/dkxocl/rosseta

공식 코드

Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism

https://github.com/dlr-rm/bpnn

공식 코드

Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks

https://github.com/dlr-rm/interactive-incremental-learning

공식 코드

Interactive incremental learning of generalizable skills with local trajectory modulation

https://github.com/dlr-rm/recall

공식 코드

RECALL: Rehearsal-free Continual Learning for Object Classification

https://github.com/dongsky/mr-gdino

공식 코드

MR-GDINO: Efficient Open-World Continual Object Detection

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