Dmitrii Marin

• PhD Student at The University of Waterloo

Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly supervised settings, e.g. where a fraction of pixels is labeled or when only image-level tags are available. It has been shown that regularized losses - originally develop...

We are interested in unsupervised reconstruction of complex near-capillary vasculature with thousands of bifurcations where supervision and learning are infeasible. Unsupervised methods can use many structural constraints, e.g. topology, geometry, physics. Common techniques use variants of MST on geodesic tubular graphs minimizing symmetric pairwis...

Many automated processes such as auto-piloting rely on a good semantic segmentation as a critical component. To speed up performance, it is common to downsample the input frame. However, this comes at the cost of missed small objects and reduced accuracy at semantic boundaries. To address this problem, we propose a new content-adaptive downsampling...

This work bridges the gap between two popular methodologies for data partitioning: kernel clustering and regularization-based segmentation. While addressing closely related practical problems, these general methodologies may seem very different based on how they are covered in the literature. The differences may show up in motivation, formulation,...

The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization. In the context of weakly-supervised CNN segmentation, we demonstrate a well-motivated loss function where an altern...

We propose a new geometric regularization principle for reconstructing vector fields based on prior knowledge about their divergence. As one important example of this general idea, we focus on vector fields modelling blood flow pattern that should be divergent in arteries and convergent in veins. We show that this previously ignored regularization...

Variants of gradient descent (GD) dominate CNN loss minimization in computer vision. But, as we show, some powerful loss functions are practically useless only due to their poor optimization by GD. In the context of weakly-supervised CNN segmentation, we present a general ADM approach to regularized losses, which are inspired by well-known MRF/CRF...

Clustering is widely used in data analysis where kernel methods are particularly popular due to their generality and discriminating power. However, kernel clustering has a practically significant bias to small dense clusters, e.g. empirically observed in (Shi and Malik, TPAMI'00). Its causes have never been analyzed and understood theoretically, ev...

Kernel methods are popular in clustering due to their generality and discriminating power. However, we show that many kernel clustering criteria have density biases theoretically explaining some practically significant artifacts empirically observed in the past. For example, we provide conditions and formally prove the density mode isolation bias i...

We propose a new segmentation or clustering model that combines Markov Random Field (MRF) and Normalized Cut (NC) objectives. Both NC and MRF models are widely used in machine learning and computer vision, but they were not combined before due to significant differences in the corresponding optimization, e.g. spectral relaxation and combinatorial m...

The log-likelihood energy term in popular model-fitting segmentation methods, e.g. Zhu-Yuille, Chan-Vese, GrabCut, etc., is presented as a generalized "probabilistic" K-means energy for color space clustering. This interpretation reveals some limitations, e.g. over-fitting. We propose an alternative approach to color clustering using kernel K-means...

Many applications in vision require estimation of thin structures such as boundary edges, surfaces, roads, blood vessels, neurons, etc. Unlike most previous approaches, we simultaneously detect and delineate thin structures with sub-pixel localization and real-valued orientation estimation. This is an ill-posed problem that requires regularization....