https://github.com/dawnvince/mts_cad
공식 코드Beyond Sharing: Conflict-Aware Multivariate Time Series Anomaly Detection
Papers with Code 아카이브
Transfer Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 6
- 보존된 평가 기록
- 10
Transfer Learning is a machine learning technique where a model trained on one task is re-purposed and fine-tuned for a related, but different task. The idea behind transfer learning is to leverage the knowledge learned from a pre-trained model to solve a new, but related problem. This can be useful in situations where there is limited data available to train a new model from scratch, or when the new task is similar enough to the original task that the pre-trained model can be adapted to the new problem with only minor modifications.
<span style="color:grey; opacity: 0.6">( Image credit: Subodh Malgonde )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/dayu11/selective_pretraining_for_private_finetuning
공식 코드https://github.com/dazcona/mrnet
공식 코드https://github.com/db-lee/selfsup_dd
공식 코드https://github.com/dbolya/parc
공식 코드Scalable Diverse Model Selection for Accessible Transfer Learning
https://github.com/dbouchabou/using-language-model-to-bootstrap-human-activity-recognition-in-smart-homes
공식 코드Using Language Model to Bootstrap Human Activity Recognition Ambient Sensors Based in Smart Homes
https://github.com/dcgm/pero-pretraining
공식 코드https://github.com/dchen48/e3ac
공식 코드${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
https://github.com/dddavid4real/HistGen
공식 코드https://github.com/dddzg/up-detr
공식 코드UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
https://github.com/ddlbojack/mt4ssl
공식 코드MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets
https://github.com/ddursun/violence-detection
공식 코드Comparative Analysis: Violence Recognition from Videos using Transfer Learning
https://github.com/debapriya-tula/tascnet
공식 코드Target Aware Network Architecture Search and Compression for Efficient Knowledge Transfer
https://github.com/debatelab/aacorpus
공식 코드https://github.com/debjyoti385/jackpine
공식 코드https://github.com/debjyoti385/osm_benchmark
공식 코드https://github.com/debjyoti385/workload_scripts
공식 코드https://github.com/declare-lab/knot
공식 코드KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks
https://github.com/declare-lab/resta
공식 코드https://github.com/declare-lab/sinkhorn-loss
공식 코드KNOT: Knowledge Distillation using Optimal Transport for Solving NLP Tasks
https://github.com/declare-lab/speech-adapters
공식 코드https://github.com/deep-analysis-research/slta
공식 코드Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
https://github.com/deep-spin/OpenNMT-APE
공식 코드A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning
https://github.com/deepgraphlearning/peer_benchmark
공식 코드PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding
https://github.com/deepinsight/insightface
공식 코드RetinaFace: Single-stage Dense Face Localisation in the Wild
https://github.com/deeplearnxmu/unigencoder
공식 코드UniGenCoder: Merging Seq2Seq and Seq2Tree Paradigms for Unified Code Generation
https://github.com/deepmicroscopy/ami-br_benchmark
공식 코드https://github.com/deepmind/deepmind-research/tree/master/gated_linear_networks
공식 코드https://github.com/deepmind/detcon
공식 코드https://github.com/deepmind/dm_nevis
공식 코드NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
https://github.com/deepopinion/domain-adapted-atsc
공식 코드https://github.com/deeppsp/cinc2022
공식 코드Searching for Effective Neural Network Architectures for Heart Murmur Detection from Phonocardiogram
https://github.com/deepseek-ai/DeepEP
공식 코드A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications
https://github.com/deepseek-ai/deepseek-r1
공식 코드DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
https://github.com/defaultrui/vln-ver
공식 코드Volumetric Environment Representation for Vision-Language Navigation
https://github.com/dehanalkautsar/indotod
공식 코드IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.