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/idiap/analogy_learning
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
https://github.com/idiap/mhan
https://github.com/iesl/geometric_graph_embedding
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
https://github.com/ifding/simple-Infomax-pytorch
Learning deep representations by mutual information estimation and maximization
https://github.com/igorsterner/commute-opt-gnn
https://github.com/ikergarcia1996/easy-label-projection
https://github.com/ilhamfp/indonesian-text-classification-multilingual
https://github.com/ilkhem/icebeem
Variational Autoencoders and Nonlinear ICA: A Unifying Framework
https://github.com/ilkhem/ivae
Variational Autoencoders and Nonlinear ICA: A Unifying Framework
https://github.com/ilyassmoummad/ProtoCLR
https://github.com/ilyatrofimov/sftd
Representation Topology Divergence: A Method for Comparing Neural Network Representations
https://github.com/imamathcat/LASER_Dependencies
Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings
https://github.com/imoonlab/deephypergraph
https://github.com/imoonlab/hyper-yolo
https://github.com/imoonlab/yolov13
https://github.com/imperialite/BERT-Embeddings-For-ARA
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
https://github.com/impiga/plain-detr
https://github.com/imran3180/pytorch-nli
https://github.com/inconnu11/Objective-evaluation_speech_synthesis
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
https://github.com/inejc/paragraph-vectors
https://github.com/ink-usc/request
https://github.com/inkplatform/InfoGAN-PyTorch
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
https://github.com/inmoonlight/confcrawl
A Bilingual Generative Transformer for Semantic Sentence Embedding
https://github.com/innat/DOLG-TensorFlow
DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features
https://github.com/innat/mae-spatiotemporal
https://github.com/intel/daal
DisCo: Physics-Based Unsupervised Discovery of Coherent Structures in Spatiotemporal Systems
https://github.com/intellabs/vl-interpret
KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation
https://github.com/inzva/music-generation
https://github.com/inzva/turkish-glove
https://github.com/iomanker/VQVAE-TF2
https://github.com/irmvlab/point-mamba
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
https://github.com/ironjr/grokfast
https://github.com/irynakostyshyn/A-Style-Based-Generator-Architecture-for-GAN
A Style-Based Generator Architecture for Generative Adversarial Networks
https://github.com/is90057/DCGAN
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
https://github.com/isaaccorley/hydro-foundation-model
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.