Search Results for author:
Found 13 papers, 6 papers with code
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so.
Ranked #13 on
Contrastive Learning
on imagenet-1k
Unsupervised Sketch-to-Photo Synthesis
Humans can envision a realistic photo given a free-hand sketch that is not only spatially imprecise and geometrically distorted but also without colors and visual details.
High Fidelity Deep Learning-based MRI Reconstruction with Instance-wise Discriminative Feature Matching Loss
By adding an additional loss function on the low-dimensional feature space during training, the reconstruction frameworks from under-sampled or corrupted data can reproduce more realistic images that are closer to the original with finer textures, sharper edges, and improved overall image quality.
BatVision: Learning to See 3D Spatial Layout with Two Ears
Inspired by bats' echolocation mechanism, we design a low-cost BatVision system that is capable of seeing the 3D spatial layout of space ahead by just listening with two ears.
BatVision with GCC-PHAT Features for Better Sound to Vision Predictions
We improve on the previous model by introducing several changes to the model, which leads to a better depth and grayscale estimation, and increased perceptual quality.
SurReal: Complex-Valued Learning as Principled Transformations on a Scaling and Rotation Manifold
We propose to extend the property instead of the form of real-valued functions to the complex domain.
Semantic Analysis of (Reflectional) Visual Symmetry: A Human-Centred Computational Model for Declarative Explainability
Key features include a human-centred representation, and a declarative, explainable interpretation model supporting deep semantic question-answering founded on an integration of methods in knowledge representation and deep learning based computer vision.
C-SURE: Shrinkage Estimator and Prototype Classifier for Complex-Valued Deep Learning
We compare C-SURE with SurReal and a real-valued baseline on complex-valued MSTAR and RadioML datasets.
HyperReal: Complex-Valued Layer Functions For Complex-Valued Scaling Invariance
SurReal complex-valued networks adopt a manifold view of complex numbers and derive a distance metric that is invariant to complex scaling.
Contextual Image Parsing via Panoptic Segment Sorting
We aim to leverage the densely labeled task, image parsing, a. k. a panoptic segmentation, to learn a model that encodes and discovers object-centric context.
Unsupervised deep learning for grading of age-related macular degeneration using retinal fundus images
Many diseases are classified based on human-defined rubrics that are prone to bias.
CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data
We propose CO-SNE, which extends the Euclidean space visualization tool, t-SNE, to hyperbolic space.
Broad Adversarial Training with Data Augmentation in the Output Space
Using B-AT instead of AT for supervised learning, we can increase the robustness by 0. 56\% for small seen attacks.
