Personal Website

Papers, publications, and related:

Generative Probabilistic Novelty Detection with Adversarial Autoencoders

Stanislav Pidhorskyi, Ranya Almohsen, Donald Adjeroh, and Gianfranco Doretto

In: Advances in Neural Information Processing Systems (NeurIPS). 2018 , pp. 6821–6832 .

Novelty detection is the problem of identifying whether a new data point is considered to be an inlier or an outlier. We assume that training data is available to describe only the inlier distribution. Recent approaches primarily leverage deep encoder-decoder network architectures to compute a reconstruction error that is used to either compute a novelty score or to train a one-class classifier. While we too leverage a novel network of that kind, we take a probabilistic approach and effectively compute how likely is that a sample was generated by the inlier distribution. We achieve this with two main contributions. First, we make the computation of the novelty probability feasible because we linearize the parameterized manifold capturing the underlying structure of the inlier distribution, and show how the probability factorizes and can be computed with respect to local coordinates of the manifold tangent space. Second, we improved the training of the autoencoder network. An extensive set of results show that the approach achieves state-of-the-art results on several benchmark datasets.
Read more →

Deep Supervised Hashing with Spherical Embedding

Pidhorskyi, Stanislav and Jones, Quinn and Motiian, Saeid and Adjeroh, Donald and Doretto, Gianfranc

In: Asian Conference on Computer Vision (ACCV). 2018 .

Deep hashing approaches are widely applied to approximate nearest neighbor search for large-scale image retrieval. We propose Spherical Deep Supervised Hashing (SDSH), a new supervised deep hashing approach to learn compact binary codes. The goal of SDSH is to go beyond learning similarity preserving codes, by encouraging them to also be balanced and to maximize the mean average precision. This is enabled by advocating the use of a different relaxation method, allowing the learning of a spherical embedding, which overcomes the challenge of maintaining the learning problem well-posed without the need to add extra binarizing priors. This allows the formulation of a general triplet loss framework, with the introduction of the spring loss for learning balanced codes, and of the ability to learn an embedding quantization that maximizes the mean average precision. Extensive experiments demonstrate that the approach compares favorably with the state-of-the-art while providing significant performance increase at more compact code sizes.
Read more →

syGlass: Interactive Exploration of Multidimensional Images Using Virtual Reality Head-mounted Displays

Pidhorskyi, Stanislav and Morehead, Michael and Jones, Quinn and Spirou, George and Doretto, Gianfranco

In: arXiv preprint arXiv:1804.08197. 2018 .

The quest for deeper understanding of biological systems has driven the acquisition of increasingly larger multi-dimensional image datasets. Inspecting and manipulating data of this complexity is very challenging in traditional visualization systems. We developed syGlass, a software package capable of visualizing large-scale volumetric data with inexpensive virtual reality head-mounted display technology. This allows leveraging stereoscopic vision to significantly improve perception of complex 3D structures, and provides immersive interaction with data directly in 3D. We accomplished this by developing highly optimized data flow and volume rendering pipelines, tested on datasets up to 16TB in size, as well as tools available in a virtual reality GUI to support advanced data exploration, annotation, and cataloging.
Read more →

Open-set Recognition with Adversarial Autoencoders

Almohsen, Ranya and Pidhorskyi, Stanislav and Doretto, Gianfranco

In: WiML Workshop. 2018 .

Read more →