Models, code, and papers for "Alexander Kirillov":

Calculated attributes of synonym sets

Mar 05, 2018
Andrew Krizhanovsky, Alexander Kirillov

The goal of formalization, proposed in this paper, is to bring together, as near as possible, the theoretic linguistic problem of synonym conception and the computer linguistic methods based generally on empirical intuitive unjustified factors. Using the word vector representation we have proposed the geometric approach to mathematical modeling of synonym set (synset). The word embedding is based on the neural networks (Skip-gram, CBOW), developed and realized as word2vec program by T. Mikolov. The standard cosine similarity is used as the distance between word-vectors. Several geometric characteristics of the synset words are introduced: the interior of synset, the synset word rank and centrality. These notions are intended to select the most significant synset words, i.e. the words which senses are the nearest to the sense of a synset. Some experiments with proposed notions, based on RusVectores resources, are represented. A brief description of this work can be viewed in slides https://goo.gl/K82Fei

* 6 pages, 2 tables, 2 figures, preprint 

  Click for Model/Code and Paper
WSD algorithm based on a new method of vector-word contexts proximity calculation via epsilon-filtration

Jun 18, 2018
Alexander Kirillov, Natalia Krizhanovsky, Andrew Krizhanovsky

The problem of word sense disambiguation (WSD) is considered in the article. Given a set of synonyms (synsets) and sentences with these synonyms. It is necessary to select the meaning of the word in the sentence automatically. 1285 sentences were tagged by experts, namely, one of the dictionary meanings was selected by experts for target words. To solve the WSD-problem, an algorithm based on a new method of vector-word contexts proximity calculation is proposed. In order to achieve higher accuracy, a preliminary epsilon-filtering of words is performed, both in the sentence and in the set of synonyms. An extensive program of experiments was carried out. Four algorithms are implemented, including a new algorithm. Experiments have shown that in a number of cases the new algorithm shows better results. The developed software and the tagged corpus have an open license and are available online. Wiktionary and Wikisource are used. A brief description of this work can be viewed in slides (https://goo.gl/9ak6Gt). Video lecture in Russian on this research is available online (https://youtu.be/-DLmRkepf58).

* Transactions of Karelian Research Centre RAS. No. 7. 2018. P. 149-163 
* 15 pages, 1 table, 15 figures, accepted in the journal Transactions of Karelian Research Centre of the Russian Academy of Sciences 

  Click for Model/Code and Paper
Exploring Randomly Wired Neural Networks for Image Recognition

Apr 08, 2019
Saining Xie, Alexander Kirillov, Ross Girshick, Kaiming He

Neural networks for image recognition have evolved through extensive manual design from simple chain-like models to structures with multiple wiring paths. The success of ResNets and DenseNets is due in large part to their innovative wiring plans. Now, neural architecture search (NAS) studies are exploring the joint optimization of wiring and operation types, however, the space of possible wirings is constrained and still driven by manual design despite being searched. In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks. To do this, we first define the concept of a stochastic network generator that encapsulates the entire network generation process. Encapsulation provides a unified view of NAS and randomly wired networks. Then, we use three classical random graph models to generate randomly wired graphs for networks. The results are surprising: several variants of these random generators yield network instances that have competitive accuracy on the ImageNet benchmark. These results suggest that new efforts focusing on designing better network generators may lead to new breakthroughs by exploring less constrained search spaces with more room for novel design.

* Technical report 

  Click for Model/Code and Paper
Panoptic Feature Pyramid Networks

Jan 08, 2019
Alexander Kirillov, Ross Girshick, Kaiming He, Piotr Dollár

The recently introduced panoptic segmentation task has renewed our community's interest in unifying the tasks of instance segmentation (for thing classes) and semantic segmentation (for stuff classes). However, current state-of-the-art methods for this joint task use separate and dissimilar networks for instance and semantic segmentation, without performing any shared computation. In this work, we aim to unify these methods at the architectural level, designing a single network for both tasks. Our approach is to endow Mask R-CNN, a popular instance segmentation method, with a semantic segmentation branch using a shared Feature Pyramid Network (FPN) backbone. Surprisingly, this simple baseline not only remains effective for instance segmentation, but also yields a lightweight, top-performing method for semantic segmentation. In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks. Given its effectiveness and conceptual simplicity, we hope our method can serve as a strong baseline and aid future research in panoptic segmentation.

* tech report 

  Click for Model/Code and Paper
Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization

Jun 23, 2016
Alexander Kirillov, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy

We consider the problem of jointly inferring the M-best diverse labelings for a binary (high-order) submodular energy of a graphical model. Recently, it was shown that this problem can be solved to a global optimum, for many practically interesting diversity measures. It was noted that the labelings are, so-called, nested. This nestedness property also holds for labelings of a class of parametric submodular minimization problems, where different values of the global parameter $\gamma$ give rise to different solutions. The popular example of the parametric submodular minimization is the monotonic parametric max-flow problem, which is also widely used for computing multiple labelings. As the main contribution of this work we establish a close relationship between diversity with submodular energies and the parametric submodular minimization. In particular, the joint M-best diverse labelings can be obtained by running a non-parametric submodular minimization (in the special case - max-flow) solver for M different values of $\gamma$ in parallel, for certain diversity measures. Importantly, the values for $\gamma$ can be computed in a closed form in advance, prior to any optimization. These theoretical results suggest two simple yet efficient algorithms for the joint M-best diverse problem, which outperform competitors in terms of runtime and quality of results. In particular, as we show in the paper, the new methods compute the exact M-best diverse labelings faster than a popular method of Batra et al., which in some sense only obtains approximate solutions.


  Click for Model/Code and Paper
Panoptic Segmentation

Apr 14, 2018
Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, Piotr Dollár

We propose and study a novel panoptic segmentation (PS) task. Panoptic segmentation unifies the typically distinct tasks of semantic segmentation (assign a class label to each pixel) and instance segmentation (detect and segment each object instance). The proposed task requires generating a coherent scene segmentation that is rich and complete, an important step toward real-world vision systems. While early work in computer vision addressed related image/scene parsing tasks, these are not currently popular, possibly due to lack of appropriate metrics or associated recognition challenges. To address this, we first propose a novel panoptic quality (PQ) metric that captures performance for all classes (stuff and things) in an interpretable and unified manner. Using the proposed metric, we perform a rigorous study of both human and machine performance for PS on three existing datasets, revealing interesting insights about the task. Second, we are working to introduce panoptic segmentation tracks at upcoming recognition challenges. The aim of our work is to revive the interest of the community in a more unified view of image segmentation.

* update of related work and metric details 

  Click for Model/Code and Paper
InstanceCut: from Edges to Instances with MultiCut

Nov 24, 2016
Alexander Kirillov, Evgeny Levinkov, Bjoern Andres, Bogdan Savchynskyy, Carsten Rother

This work addresses the task of instance-aware semantic segmentation. Our key motivation is to design a simple method with a new modelling-paradigm, which therefore has a different trade-off between advantages and disadvantages compared to known approaches. Our approach, we term InstanceCut, represents the problem by two output modalities: (i) an instance-agnostic semantic segmentation and (ii) all instance-boundaries. The former is computed from a standard convolutional neural network for semantic segmentation, and the latter is derived from a new instance-aware edge detection model. To reason globally about the optimal partitioning of an image into instances, we combine these two modalities into a novel MultiCut formulation. We evaluate our approach on the challenging CityScapes dataset. Despite the conceptual simplicity of our approach, we achieve the best result among all published methods, and perform particularly well for rare object classes.

* The code would be released at https://github.com/alexander-kirillov/InstanceCut 

  Click for Model/Code and Paper
Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation

Feb 26, 2017
Omid Hosseini Jafari, Oliver Groth, Alexander Kirillov, Michael Ying Yang, Carsten Rother

This paper addresses the task of designing a modular neural network architecture that jointly solves different tasks. As an example we use the tasks of depth estimation and semantic segmentation given a single RGB image. The main focus of this work is to analyze the cross-modality influence between depth and semantic prediction maps on their joint refinement. While most previous works solely focus on measuring improvements in accuracy, we propose a way to quantify the cross-modality influence. We show that there is a relationship between final accuracy and cross-modality influence, although not a simple linear one. Hence a larger cross-modality influence does not necessarily translate into an improved accuracy. We find that a beneficial balance between the cross-modality influences can be achieved by network architecture and conjecture that this relationship can be utilized to understand different network design choices. Towards this end we propose a Convolutional Neural Network (CNN) architecture that fuses the state of the state-of-the-art results for depth estimation and semantic labeling. By balancing the cross-modality influences between depth and semantic prediction, we achieve improved results for both tasks using the NYU-Depth v2 benchmark.

* Accepted to ICRA 2017 

  Click for Model/Code and Paper
Global Hypothesis Generation for 6D Object Pose Estimation

Jan 02, 2017
Frank Michel, Alexander Kirillov, Eric Brachmann, Alexander Krull, Stefan Gumhold, Bogdan Savchynskyy, Carsten Rother

This paper addresses the task of estimating the 6D pose of a known 3D object from a single RGB-D image. Most modern approaches solve this task in three steps: i) Compute local features; ii) Generate a pool of pose-hypotheses; iii) Select and refine a pose from the pool. This work focuses on the second step. While all existing approaches generate the hypotheses pool via local reasoning, e.g. RANSAC or Hough-voting, we are the first to show that global reasoning is beneficial at this stage. In particular, we formulate a novel fully-connected Conditional Random Field (CRF) that outputs a very small number of pose-hypotheses. Despite the potential functions of the CRF being non-Gaussian, we give a new and efficient two-step optimization procedure, with some guarantees for optimality. We utilize our global hypotheses generation procedure to produce results that exceed state-of-the-art for the challenging "Occluded Object Dataset".


  Click for Model/Code and Paper
Joint Training of Generic CNN-CRF Models with Stochastic Optimization

Sep 14, 2016
Alexander Kirillov, Dmitrij Schlesinger, Shuai Zheng, Bogdan Savchynskyy, Philip H. S. Torr, Carsten Rother

We propose a new CNN-CRF end-to-end learning framework, which is based on joint stochastic optimization with respect to both Convolutional Neural Network (CNN) and Conditional Random Field (CRF) parameters. While stochastic gradient descent is a standard technique for CNN training, it was not used for joint models so far. We show that our learning method is (i) general, i.e. it applies to arbitrary CNN and CRF architectures and potential functions; (ii) scalable, i.e. it has a low memory footprint and straightforwardly parallelizes on GPUs; (iii) easy in implementation. Additionally, the unified CNN-CRF optimization approach simplifies a potential hardware implementation. We empirically evaluate our method on the task of semantic labeling of body parts in depth images and show that it compares favorably to competing techniques.

* ACCV2016 

  Click for Model/Code and Paper
Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications

Feb 21, 2017
Evgeny Levinkov, Jonas Uhrig, Siyu Tang, Mohamed Omran, Eldar Insafutdinov, Alexander Kirillov, Carsten Rother, Thomas Brox, Bernt Schiele, Bjoern Andres

We state a combinatorial optimization problem whose feasible solutions define both a decomposition and a node labeling of a given graph. This problem offers a common mathematical abstraction of seemingly unrelated computer vision tasks, including instance-separating semantic segmentation, articulated human body pose estimation and multiple object tracking. Conceptually, the problem we state generalizes the unconstrained integer quadratic program and the minimum cost lifted multicut problem, both of which are NP-hard. In order to find feasible solutions efficiently, we define two local search algorithms that converge monotonously to a local optimum, offering a feasible solution at any time. To demonstrate their effectiveness in tackling computer vision tasks, we apply these algorithms to instances of the problem that we construct from published data, using published algorithms. We report state-of-the-art application-specific accuracy for the three above-mentioned applications.


  Click for Model/Code and Paper
OntoMath Digital Ecosystem: Ontologies, Mathematical Knowledge Analytics and Management

Feb 16, 2017
Alexander Elizarov, Alexander Kirillovich, Evgeny Lipachev, Olga Nevzorova

In this article we consider the basic ideas, approaches and results of developing of mathematical knowledge management technologies based on ontologies. These solutions form the basis of a specialized digital ecosystem OntoMath which consists of the ontology of the logical structure of mathematical documents Mocassin and ontology of mathematical knowledge OntoMathPRO, tools of text analysis, recommender system and other applications to manage mathematical knowledge. The studies are in according to the ideas of creating a distributed system of interconnected repositories of digitized versions of mathematical documents and project to create a World Digital Mathematical Library.


  Click for Model/Code and Paper
$OntoMath^{PRO}$ Ontology: A Linked Data Hub for Mathematics

Aug 11, 2014
Olga Nevzorova, Nikita Zhiltsov, Alexander Kirillovich, Evgeny Lipachev

In this paper, we present an ontology of mathematical knowledge concepts that covers a wide range of the fields of mathematics and introduces a balanced representation between comprehensive and sensible models. We demonstrate the applications of this representation in information extraction, semantic search, and education. We argue that the ontology can be a core of future integration of math-aware data sets in the Web of Data and, therefore, provide mappings onto relevant datasets, such as DBpedia and ScienceWISE.

* 15 pages, 6 images, 1 table, Knowledge Engineering and the Semantic Web - 5th International Conference 

  Click for Model/Code and Paper
Mathematical Knowledge Representation: Semantic Models and Formalisms

Aug 29, 2014
Alexander Elizarov, Alexander Kirillovich, Evgeny Lipachev, Olga Nevzorova, Valery Solovyev, Nikita Zhiltsov

The paper provides a survey of semantic methods for solution of fundamental tasks in mathematical knowledge management. Ontological models and formalisms are discussed. We propose an ontology of mathematical knowledge, covering a wide range of fields of mathematics. We demonstrate applications of this representation in mathematical formula search, and learning.

* 10 pages, Lobachevskii J. of Mathematics, 2014, V.35, No 4 

  Click for Model/Code and Paper