Homography augumented momentum constrastive learning for SAR image retrieval
arXiv:2109.10329
Abstract
Deep learning-based image retrieval has been emphasized in computer vision. Representation embedding extracted by deep neural networks (DNNs) not only aims at containing semantic information of the image, but also can manage large-scale image retrieval tasks. In this work, we propose a deep learning-based image retrieval approach using homography transformation augmented contrastive learning to perform large-scale synthetic aperture radar (SAR) image search tasks. Moreover, we propose a training method for the DNNs induced by contrastive learning that does not require any labeling procedure. This may enable tractability of large-scale datasets with relative ease. Finally, we verify the performance of the proposed method by conducting experiments on the polarimetric SAR image datasets.
References in corpus (11)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Distilling the Knowledge in a Neural Network
- Bootstrap your own latent: A new approach to self-supervised Learning
- Improved Baselines with Momentum Contrastive Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Exploring Simple Siamese Representation Learning
- Regularizing Neural Networks by Penalizing Confident Output Distributions
- Deep Image Homography Estimation
- Self-supervised Pretraining of Visual Features in the Wild
- LoFTR: Detector-Free Local Feature Matching with Transformers
- The SEN1-2 Dataset for Deep Learning in SAR-Optical Data Fusion