Short Notes on Few Interesting Papers
ML + BIO
- Visual Correspondences for Unsupervised Domain Adaptation on Electron Microscopy Images. Link
- Teaching deep neural networks to localize single molecules for super-resolution microscopy. Link
- Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization. Link
- Noise2Void - Learning Denoising from Single Noisy Images. Link
- Modality Attention and Sampling Enables Deep Learning with Heterogeneous Marker Combinations in Fluorescence Microscopy. Link
- Ultrasound Video Summarization using Deep Reinforcement Learning. Link
- Self-Supervised Representation Learning For Ultrasound Video. Link
- CLOPS: Continual Learning of Physiological Signals Link
- Joint reconstruction and bias field correction for undersampled MR imaging. Link
- A deep spatiotemporal graph learning architecture for brain connectivity analysis. Link
- Rapid whole-heart CMR with single volume super-resolution. Link
- Real‐time cardiovascular MR with spatio‐temporal artifact suppression using deep learning–proof of concept in congenital heart disease. Link
- Barking up the right tree: an approach to search over molecule synthesis DAGs. Link
- Disentangling Human Error from the Ground Truth in Segmentation of Medical Images. Link
- Time-Dependent Deep Image Prior for Dynamic MRI. Link
- Anomaly Detection on X-Rays Using Self-Supervised Aggregation Learning. Link
- Task-driven hierarchical deep neural network models of the proprioceptive pathway. Link
- End-to-end training of deep probabilistic CCA on paired biomedical observations. Link
Vision
- Rethinking Class Relations: Absolute-relative Few-shot Learning. Link
- CLIFER: Continual Learning with Imagination for Facial Expression Recognition. Link
- Category Level Object Pose Estimation via Neural Analysis-by-Synthesis. Link
- Self-Supervised Localisation between Range Sensors and Overhead Imagery. Link
- RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces. Link
- Perpetual Motion: Generating Unbounded Human Motion. Link
- Dual Resolution Corresponding Networks. Link
- Self-supervised Learning of Interpretable Key Points from Unlabelled Videos Link
- Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix. Link
Gaze Estimation
- Learning-by-Synthesis for Appearance-based 3D Gaze Estimation. Link
- 360-Degree Gaze Estimation in the Wild Using Multiple Zoom Scales. Link
- Deep eye fixation map learning for calibration-free eye gaze tracking. Link
- A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation Link
