Self-Supervised Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 208
This is the task of image classification using representations learnt with self-supervised learning. Self-supervised methods generally involve a pretext task that is solved to learn a good representation and a loss function to learn with. One example of a loss function is an autoencoder based loss where the goal is reconstruction of an image pixel-by-pixel. A more popular recent example is a contrastive loss, which measure the similarity of sample pairs in a representation space, and where there can be a varying target instead of a fixed target to reconstruct (as in the case of autoencoders).
A common evaluation protocol is to train a linear classifier on top of (frozen) representations learnt by self-supervised methods. The leaderboards for the linear evaluation protocol can be found below. In practice, it is more common to fine-tune features on a downstream task. An alternative evaluation protocol therefore uses semi-supervised learning and finetunes on a % of the labels. The leaderboards for the finetuning protocol can be accessed here.
You may want to read some blog posts before reading the papers and checking the leaderboards:
- Contrastive Self-Supervised Learning - Ankesh Anand
- The Illustrated Self-Supervised Learning - Amit Chaudhary
- Self-supervised learning and computer vision - Jeremy Howard
- Self-Supervised Representation Learning - Lilian Weng
There is also Yann LeCun's talk at AAAI-20 which you can watch here (35:00+).
<span style="color:grey; opacity: 0.6">( Image credit: A Simple Framework for Contrastive Learning of Visual Representations )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
A Pseudo-labelling Auto-Encoder for unsupervised image classification
Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning
Boosting Contrastive Self-Supervised Learning with False Negative Cancellation
Exploring Simple Siamese Representation Learning
A comparative study of semi- and self-supervised semantic segmentation of biomedical microscopy data
CompRess: Self-Supervised Learning by Compressing Representations
Representation Learning via Invariant Causal Mechanisms
Consensus Clustering With Unsupervised Representation Learning
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Big Self-Supervised Models are Strong Semi-Supervised Learners
Bootstrap your own latent: A new approach to self-supervised Learning
What Makes for Good Views for Contrastive Learning?
Prototypical Contrastive Learning of Unsupervised Representations
Improved Baselines with Momentum Contrastive Learning
A Simple Framework for Contrastive Learning of Visual Representations
Self-Supervised Learning of Pretext-Invariant Representations
Self-labelling via simultaneous clustering and representation learning
Momentum Contrast for Unsupervised Visual Representation Learning
On Mutual Information Maximization for Representation Learning
Large Scale Adversarial Representation Learning
Contrastive Multiview Coding
Learning Representations by Maximizing Mutual Information Across Views
Putting An End to End-to-End: Gradient-Isolated Learning of Representations
Data-Efficient Image Recognition with Contrastive Predictive Coding
Unsupervised Pre-Training of Image Features on Non-Curated Data
Local Aggregation for Unsupervised Learning of Visual Embeddings
Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
Revisiting Self-Supervised Visual Representation Learning
Deep Clustering for Unsupervised Learning of Visual Features
Representation Learning with Contrastive Predictive Coding
Unsupervised Representation Learning by Predicting Image Rotations
Multi-task Self-Supervised Visual Learning
Representation Learning by Learning to Count
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.