Augnet: End-to-end Unsupervised Visual Representation Learning With Image Augmentation
2021 · Mingxiang Chen, Zhanguo Chang, Haonan Lu, et al.
Abstract
Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the effective solutions to overcome such difficulties. In our work, we propose AugNet, a new deep learning training paradigm to learn image features from a collection of unlabeled pictures. We develop a method to construct the similarities between pictures as distance metrics in the embedding space by leveraging the inter-correlation between augmented versions of samples. Our experiments demonstrate that the method is able to represent the image in low dimensional space and performs competitively in downstream tasks such as image classification and image similarity comparison. Specifically, we achieved over 60% and 27% accuracy on the STL10 and CIFAR100 datasets with unsupervised clustering, respectively. Moreover, unlike many deep-learning-based image retriev
Authors
(none)
Tags
Stats
Related papers
- Contrastive Learning With Stronger Augmentations (2021)19.61
- Retrieval Augmentation For Deep Neural Networks (2021)5.84
- Unsupervised Natural Image Patch Learning (2018)8.82
- Beyond Supervised Vs. Unsupervised: Representative Benchmarking And Analysis Of Image Representation Learning (2022)8.35
- Learning Robust Visual-semantic Embeddings (2017)15.22
- Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination (2018)25.66
- Learning Test-time Augmentation For Content-based Image Retrieval (2020)5.24
- A Review Of Image Retrieval Techniques: Data Augmentation And Adversarial Learning Approaches (2024)0.00