Set Of Autoencoders Research Articles

A Collaborative Superpixelwise Autoencoder for Unsupervised Dimension Reduction in Hyperspectral Images

The dimension reduction (DR) technique plays an important role in hyperspectral image (HSI) processing. Among various DR methods, superpixel-based approaches offer flexibility in capturing spectral–spatial information and have shown great potential in HSI tasks. The superpixel-based methods divide the samples into groups and apply the DR technique to the small groups. Nevertheless, we find these methods would increase the intra-class disparity by neglecting the fact the samples from the same class may reside on different superpixels, resulting in performance decay. To address this problem, a novel unsupervised DR named the Collaborative superpixelwise Auto-Encoder (ColAE) is proposed in this paper. The ColAE begins by segmenting the HSI into different homogeneous regions using a superpixel-based method. Then, a set of Auto-Encoders (AEs) is applied to the samples within each superpixel. To reduce the intra-class disparity, a manifold loss is introduced to restrict the samples from the same class, even if located in different superpixels, to have similar representations in the code space. In this way, the compact and discriminative spectral–spatial feature is obtained. Experimental results on three HSI data sets demonstrate the promising performance of ColAE compared to existing state-of-the-art methods.

A Semi-Supervised Autoencoder-Based Approach for Protein Function Prediction

After the development of next-generation sequencing techniques, protein sequences are abundantly available. Determining the functional characteristics of these proteins is costly and time-consuming. The gap between the number of protein sequences and their corresponding functions is continuously increasing. Advanced machine-learning methods have stepped up to fill this gap. In this work, an advanced deep-learning-based approach is proposed for protein function prediction using protein sequences. A set of autoencoders is trained in a semi-supervised manner with protein sequences. Each autoencoder corresponds to a single protein function only. In particular, 932 autoencoders corresponding to 932 biological processes and 585 autoencoders corresponding to 585 molecular functions are trained separately. Reconstruction losses of each protein sample for every autoencoder are used as a feature to classify these sequences into their corresponding functions. The proposed model is tested on test protein samples and achieves promising results. This method can be easily extended to predict any number of functions having an ample amount of supporting protein sequences. All relevant codes, data and trained models are available at https://github.com/richadhanuka/PFP-Autoencoders.

Autoencoder based self-supervised test-time adaptation for medical image analysis.

Deep neural networks have been successfully applied to medical image analysis tasks like segmentation and synthesis. However, even if a network is trained on a large dataset from the source domain, its performance on unseen test domains is not guaranteed. The performance drop on data obtained differently from the network's training data is a major problem(known as domain shift) in deploying deep learning in clinical practice. Existing work focuses on retraining the model with data from the test domain, or harmonizing the test domain's data to the network training data. A common practice is to distribute a carefully-trained model to multiple users(e.g., clinical centers), and then each user uses the model to process their own data, which may have a domain shift(e.g., varying imaging parameters and machines). However, the lack of availability of the source training data and the cost of training a new model often prevents the use of known methods to solve user-specific domain shifts. Here, we ask whether we can design a model that, once distributed to users, can quickly adapt itself to each new site without expensive retraining or access to the source training data? In this paper, we propose a model that can adapt based on a single test subject during inference. The model consists of three parts, which are all neural networks: a task model(T) which performs the image analysis task like segmentation; a set of autoencoders(AEs); and a set of adaptors(As). The task model and autoencoders are trained on the source dataset and can be computationally expensive. In the deployment stage, the adaptors are trained to transform the test image and its features to minimize the domain shift as measured by the autoencoders' reconstruction loss. Only the adaptors are optimized during the testing stage with a single test subject thus is computationally efficient. The method was validated on both retinal optical coherence tomography(OCT) image segmentation and magnetic resonance imaging(MRI) T1-weighted to T2-weighted image synthesis. Our method, with its short optimization time for the adaptors(10 iterations on a single test subject) and its additional required disk space for the autoencoders(around 15MB), can achieve significant performance improvement. Our code is publicly available at: https://github.com/YufanHe/self-domain-adapted-network.