A Self Supervised StyleGAN for Image Annotation and Classification with Extremely Limited Labels
arXiv:2312.15972 · doi:10.1109/TMI.2022.3187170
Abstract
The recent success of learning-based algorithms can be greatly attributed to the immense amount of annotated data used for training. Yet, many datasets lack annotations due to the high costs associated with labeling, resulting in degraded performances of deep learning methods. Self-supervised learning is frequently adopted to mitigate the reliance on massive labeled datasets since it exploits unlabeled data to learn relevant feature representations. In this work, we propose SS-StyleGAN, a self-supervised approach for image annotation and classification suitable for extremely small annotated datasets. This novel framework adds self-supervision to the StyleGAN architecture by integrating an encoder that learns the embedding to the StyleGAN latent space, which is well-known for its disentangled properties. The learned latent space enables the smart selection of representatives from the data to be labeled for improved classification performance. We show that the proposed method attains strong classification results using small labeled datasets of sizes 50 and even 10. We demonstrate the superiority of our approach for the tasks of COVID-19 and liver tumor pathology identification.
arXiv commentAccepted to IEEE Transactions on Medical Imaging
References in corpus (17)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- A Simple Framework for Contrastive Learning of Visual Representations
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
- Improved Baselines with Momentum Contrastive Learning
- GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
- Unsupervised Representation Learning by Predicting Image Rotations
- A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
- A Simple Neural Attentive Meta-Learner
- COVID-19 Image Data Collection
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- Cost-Effective Active Learning for Deep Image Classification
- Towards Data-Efficient Learning: A Benchmark for COVID-19 CT Lung and Infection Segmentation
- High-Fidelity Image Generation With Fewer Labels
- Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks
- Collaborative Learning for Faster StyleGAN Embedding
- Analysis of Farthest Point Sampling for Approximating Geodesics in a Graph
- GMM-Based Generative Adversarial Encoder Learning