Representation Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 14
- 평가표
- 5
- 보존된 평가 기록
- 11
Representation Learning is a process in machine learning where algorithms extract meaningful patterns from raw data to create representations that are easier to understand and process. These representations can be designed for interpretability, reveal hidden features, or be used for transfer learning. They are valuable across many fundamental machine learning tasks like image classification and retrieval.
Deep neural networks can be considered representation learning models that typically encode information which is projected into a different subspace. These representations are then usually passed on to a linear classifier to, for instance, train a classifier.
Representation learning can be divided into:
- Supervised representation learning: learning representations on task A using annotated data and used to solve task B
- Unsupervised representation learning: learning representations on a task in an unsupervised way (label-free data). These are then used to address downstream tasks and reducing the need for annotated data when learning news tasks. Powerful models like GPT and BERT leverage unsupervised representation learning to tackle language tasks.
More recently, self-supervised learning (SSL) is one of the main drivers behind unsupervised representation learning in fields like computer vision and NLP.
Here are some additional readings to go deeper on the task:
- Representation Learning: A Review and New Perspectives - Bengio et al. (2012)
- A Few Words on Representation Learning - Thalles Silva
<span style="color:grey; opacity: 0.6">( Image credit: Visualizing and Understanding Convolutional Networks )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/timH6502/byol-a
BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation
https://github.com/timeseriesAI/tsai
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
https://github.com/timeseriesAI/tsai/blob/main/tsai/models/TST.py
A Transformer-based Framework for Multivariate Time Series Representation Learning
https://github.com/timgaripov/asa
https://github.com/timothewt/AdvancedGraphClustering
https://github.com/timsainb/Tensorflow-MultiGPU-VAE-GAN
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://github.com/titu1994/tf-TabNet
https://github.com/tju-drl-lab/self-supervised-rl
https://github.com/tmlr-group/CoPA
Universal Representation Learning from Multiple Domains for Few-shot Classification
https://github.com/tmlr-group/mokd
Universal Representation Learning from Multiple Domains for Few-shot Classification
https://github.com/tobias-opsahl/fact-or-fiction
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
https://github.com/toinesayan/node-classification-and-label-dependencies
A Fair Comparison of Graph Neural Networks for Graph Classification
https://github.com/tomas-gajarsky/facetorch
Pre-training strategies and datasets for facial representation learning
https://github.com/tomhata/emojigan
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://github.com/tonyPo/AMLSim_prep
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
https://github.com/topoxlab/dataset-brca-m2c
Multi-Class Cell Detection Using Spatial Context Representation
https://github.com/toshikwa/slac.pytorch
Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
https://github.com/totoroKalic/vehiclenet-mindspore
VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
https://github.com/tourdeml/robust-representation-random-convolutions
Robust and Generalizable Visual Representation Learning via Random Convolutions
https://github.com/towhee-io/towhee
UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning
https://github.com/tqbl/arca23k-baseline
ARCA23K: An audio dataset for investigating open-set label noise
https://github.com/trackinglaboratory/tracklab
Body Part-Based Representation Learning for Occluded Person Re-Identification
https://github.com/tractableai/perceptual-mae
Improving Visual Representation Learning through Perceptual Understanding
https://github.com/tranc012/SMILE-Rep
Momentum Contrast for Unsupervised Visual Representation Learning
https://github.com/tranhungnghiep/AnalyzingKGEmbeddings
https://github.com/transducens/LASERtrain
Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings
https://github.com/travishsu/ReConPatch-TF
ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection
https://github.com/trhgu/awesome-fashion-contents
Style2Vec: Representation Learning for Fashion Items from Style Sets
https://github.com/trungpx/solo-learn-1214
https://github.com/tsandefer/capstone_2
An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation
https://github.com/tsandefer/dsi_capstone_2
An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation
https://github.com/ttt496/vit-pytorch
https://github.com/tum-vision/intrinsic-neural-fields
Sign and Basis Invariant Networks for Spectral Graph Representation Learning
https://github.com/tutelalabs/tutela-app
https://github.com/tuvuumass/SCoPE
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.