A survey on Semi-, Self- and Unsupervised Learning for Image Classification

Abstract

While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an amount of labeled training data. Therefore, it is common to incorporate unlabeled data into the training process to reach equal results with fewer labels. Due to a lot of concurrent research, it is difficult to keep track of recent developments. In this survey, we provide an overview of often used ideas and methods in image classification with fewer labels. We compare 34 methods in detail based on their performance and their commonly used ideas rather than a fine-grained taxonomy. In our analysis, we identify three major trends that lead to future research opportunities. 1. State-of-the-art methods are scaleable to real-world applications in theory but issues like class imbalance, robustness, or fuzzy labels are not considered. 2. The degree of supervision which is needed to achieve comparable results to the usage of all labels is decreasing and therefore methods need to be extended to settings with a variable number of classes. 3. All methods share some common ideas but we identify clusters of methods that do not share many ideas. We show that combining ideas from different clusters can lead to better performance.

arXiv commentAccepted to IEEE Access 2021

References in corpus (29)

• A Simple Framework for Contrastive Learning of Visual Representations
• Representation Learning with Contrastive Predictive Coding
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• YOLOv3: An Incremental Improvement
• mixup: Beyond Empirical Risk Minimization
• Generative Adversarial Networks
• Bootstrap your own latent: A new approach to self-supervised Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Improved Baselines with Momentum Contrastive Learning
• Learning deep representations by mutual information estimation and maximization
• Unsupervised Data Augmentation for Consistency Training
• Unsupervised Representation Learning by Predicting Image Rotations
• Temporal Ensembling for Semi-Supervised Learning
• Interpolation Consistency Training for Semi-Supervised Learning
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Learning Representations by Maximizing Mutual Information Across Views
• Big Self-Supervised Models are Strong Semi-Supervised Learners
• Shake-Shake regularization
• Learning Discrete Representations via Information Maximizing Self-Augmented Training
• On Mutual Information Maximization for Representation Learning
• On Variational Bounds of Mutual Information
• There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
• Intriguing Properties of Contrastive Losses
• BYOL works even without batch statistics
• 2D and 3D Segmentation of uncertain local collagen fiber orientations in SHG microscopy
• EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble Transformations
• Isometric Propagation Network for Generalized Zero-shot Learning
• Improvability Through Semi-Supervised Learning: A Survey of Theoretical Results

Cited by in corpus (18)

• Self-supervised learning methods and applications in medical imaging analysis: A survey
• Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works
• Conservation Tools: The Next Generation of Engineering--Biology Collaborations
• Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR
• Image-to-Image Translation: Methods and Applications
• A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
• Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering
• Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy
• Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
• FLEE-GNN: A Federated Learning System for Edge-Enhanced Graph Neural Network in Analyzing Geospatial Resilience of Multicommodity Food Flows
• Parkinson gait modelling from an anomaly deep representation
• An efficient unsupervised classification model for galaxy morphology: Voting clustering based on coding from ConvNeXt large model
• Learnable Adaptive Cosine Estimator (LACE) for Image Classification
• Advancing biological super-resolution microscopy through deep learning: a brief review
• Unsupervised Learning for Industrial Defect Detection: A Case Study on Shearographic Data
• Beyond holography: the entropic quantum gravity foundations of image processing
• Life is not black and white -- Combining Semi-Supervised Learning with fuzzy labels
• FROST: Faster and more Robust One-shot Semi-supervised Training