https://github.com/lxtGH/CAE
Context Autoencoder for Self-Supervised Representation Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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:
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:
<span style="color:grey; opacity: 0.6">( Image credit: Visualizing and Understanding Convolutional Networks )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Context Autoencoder for Self-Supervised Representation Learning
DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
Deep Over-sampling Framework for Classifying Imbalanced Data
Dialogue Act Classification with Context-Aware Self-Attention
Generative Action Description Prompts for Skeleton-based Action Recognition
What you can cram into a single vector: Probing sentence embeddings for linguistic properties
Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding Manifold
Effectiveness of self-supervised pre-training for speech recognition
Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
A Style-Based Generator Architecture for Generative Adversarial Networks
A Style-Based Generator Architecture for Generative Adversarial Networks
Unsupervised Cross-lingual Representation Learning for Speech Recognition
SSD: A Unified Framework for Self-Supervised Outlier Detection
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Parametric Classification for Generalized Category Discovery: A Baseline Study
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.