arXiv subjects

Siddharth Srivastava

Publications and source records attributed to Siddharth Srivastava.

69 records · Page 4Linked to original sources

arXiv2018

Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms

Despite the recent successes of probabilistic programming languages (PPLs) in AI applications, PPLs offer only limited support for random variables whose distributions combine discrete and continuous elements. We develop the notion of measure-theoretic Bayesian networks (MTBNs) and use it to provide more general semantics for PPLs with arbitrarily many random variables defined over arbitrary measure spaces. We develop two new general sampling algorithms that are provably correct under the MTBN framework: the lexicographic likelihood weighting (LLW) for general MTBNs and the lexicographic particle filter (LPF), a specialized algorithm for state-space models. We further integrate MTBNs into a widely used PPL system, BLOG, and verify the effectiveness of the new inference algorithms through representative examples.

cs.AI↗

arXiv2018

Large Scale Novel Object Discovery in 3D

We present a method for discovering never-seen-before objects in 3D point clouds obtained from sensors like Microsoft Kinect. We generate supervoxels directly from the point cloud data and use them with a Siamese network, built on a recently proposed 3D convolutional neural network architecture. We use known objects to train a non-linear embedding of supervoxels, by optimizing the criteria that supervoxels which fall on the same object should be closer than those which fall on different objects, in the embedding space. We test on unknown objects, which were not seen during training, and perform clustering in the learned embedding space of supervoxels to effectively perform novel object discovery. We validate the method with extensive experiments, quantitatively showing that it can discover numerous unseen objects while being trained on only a few dense 3D models. We also show very good qualitative results of object discovery in point cloud data when the test objects, either specific instances or even categories, were never seen during training.

cs.CV↗

arXiv2018

Hierarchical Expertise-Level Modeling for User Specific Robot-Behavior Explanations

There is a growing interest within the AI research community to develop autonomous systems capable of explaining their behavior to users. One aspect of the explanation generation problem that has yet to receive much attention is the task of explaining plans to users whose level of expertise differ from that of the explainer. We propose an approach for addressing this problem by representing the user's model as an abstraction of the domain model that the planner uses. We present algorithms for generating minimal explanations in cases where this abstract human model is not known. We reduce the problem of generating explanation to a search over the space of abstract models and investigate possible greedy approximations for minimal explanations. We also empirically show that our approach can efficiently compute explanations for a variety of problems.

cs.AI↗

arXiv2018

An Anytime Algorithm for Task and Motion MDPs

Integrated task and motion planning has emerged as a challenging problem in sequential decision making, where a robot needs to compute high-level strategy and low-level motion plans for solving complex tasks. While high-level strategies require decision making over longer time-horizons and scales, their feasibility depends on low-level constraints based upon the geometries and continuous dynamics of the environment. The hybrid nature of this problem makes it difficult to scale; most existing approaches focus on deterministic, fully observable scenarios. We present a new approach where the high-level decision problem occurs in a stochastic setting and can be modeled as a Markov decision process. In contrast to prior efforts, we show that complete MDP policies, or contingent behaviors, can be computed effectively in an anytime fashion. Our algorithm continuously improves the quality of the solution and is guaranteed to be probabilistically complete. We evaluate the performance of our approach on a challenging, realistic test problem: autonomous aircraft inspection. Our results show that we can effectively compute consistent task and motion policies for the most likely execution-time outcomes using only a fraction of the computation required to develop the complete task and motion policy.

cs.AI↗

arXiv2017

Object Classification using Ensemble of Local and Deep Features

In this paper we propose an ensemble of local and deep features for object classification. We also compare and contrast effectiveness of feature representation capability of various layers of convolutional neural network. We demonstrate with extensive experiments for object classification that the representation capability of features from deep networks can be complemented with information captured from local features. We also find out that features from various deep convolutional networks encode distinctive characteristic information. We establish that, as opposed to conventional practice, intermediate layers of deep networks can augment the classification capabilities of features obtained from fully connected layers.

cs.CV↗

arXiv2017

Enhanced Characterness for Text Detection in the Wild

Text spotting is an interesting research problem as text may appear at any random place and may occur in various forms. Moreover, ability to detect text opens the horizons for improving many advanced computer vision problems. In this paper, we propose a novel language agnostic text detection method utilizing edge enhanced Maximally Stable Extremal Regions in natural scenes by defining strong characterness measures. We show that a simple combination of characterness cues help in rejecting the non text regions. These regions are further fine-tuned for rejecting the non-textual neighbor regions. Comprehensive evaluation of the proposed scheme shows that it provides comparative to better generalization performance to the traditional methods for this task.

cs.CV↗

arXiv2017

Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55

We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet 3D object database. The benchmark consists of two tasks: part-level segmentation of 3D shapes and 3D reconstruction from single view images. Ten teams have participated in the challenge and the best performing teams have outperformed state-of-the-art approaches on both tasks. A few novel deep learning architectures have been proposed on various 3D representations on both tasks. We report the techniques used by each team and the corresponding performances. In addition, we summarize the major discoveries from the reported results and possible trends for the future work in the field.

cs.CV↗

arXiv2017

Drought Stress Classification using 3D Plant Models

Quantification of physiological changes in plants can capture different drought mechanisms and assist in selection of tolerant varieties in a high throughput manner. In this context, an accurate 3D model of plant canopy provides a reliable representation for drought stress characterization in contrast to using 2D images. In this paper, we propose a novel end-to-end pipeline including 3D reconstruction, segmentation and feature extraction, leveraging deep neural networks at various stages, for drought stress study. To overcome the high degree of self-similarities and self-occlusions in plant canopy, prior knowledge of leaf shape based on features from deep siamese network are used to construct an accurate 3D model using structure from motion on wheat plants. The drought stress is characterized with a deep network based feature aggregation. We compare the proposed methodology on several descriptors, and show that the network outperforms conventional methods.

cs.CV↗

arXiv2017

3D Binary Signatures

In this paper, we propose a novel binary descriptor for 3D point clouds. The proposed descriptor termed as 3D Binary Signature (3DBS) is motivated from the matching efficiency of the binary descriptors for 2D images. 3DBS describes keypoints from point clouds with a binary vector resulting in extremely fast matching. The method uses keypoints from standard keypoint detectors. The descriptor is built by constructing a Local Reference Frame and aligning a local surface patch accordingly. The local surface patch constitutes of identifying nearest neighbours based upon an angular constraint among them. The points are ordered with respect to the distance from the keypoints. The normals of the ordered pairs of these keypoints are projected on the axes and the relative magnitude is used to assign a binary digit. The vector thus constituted is used as a signature for representing the keypoints. The matching is done by using hamming distance. We show that 3DBS outperforms state of the art descriptors on various evaluation metrics.

cs.CV↗

arXiv2017

An ROS-based Shared Communication Middleware for Plug & Play Modular Intelligent Design of Smart Systems

Centralized architectures for systems such as smart offices and homes are rapidly becoming obsolete due to inherent inflexibility in their design and management. This is because such systems should not only be easily re-configurable with the addition of newer capabilities over time but should also have the ability to adapt to multiple points of failure. Fully harnessing the capabilities of these massively integrated systems requires higher level reasoning engines that allow them to plan for and achieve diverse long-term goals, rather than being limited to a few predefined tasks. In this paper, we propose a set of properties that will accommodate such capabilities, and develop a general architecture for integrating automated planning components into smart systems. We show how the reasoning capabilities are embedded in the design and operation of the system and demonstrate the same on a real-world implementation of a smart office.

cs.RO↗

arXiv2015

Electronic Health Records and Cloud based Generic Medical Equipment Interface

Now-a-days Health Care industry is well equipped with Medical Equipments to provide accurate and timely reports of investigation and examination results. Medical Equipments available in market are made for specific tests suited for a particular laboratory leading to a wide variety of devices. The result viewing experience on console of these devices is not only cumborsome for medical staff but inefficient. Therefore, Medical Equipment Interfaces act as backbone of any Hospital Management Information System assisting in better management and delivery of test results. It also acts as a mode to collect data for further research and analysis. These equipments communicate via a fixed data format but compatibility among these formats is a major issue being faced in modern and legacy medical equipments. In this paper, we present a case study of designing and implementing a cloud based Generic Medical Equipment Interface(GMEI) along with the state of the art in such systems. This solution removes the burden of reentry of patient details into the Electronic Health Record(EHR) and thrives for accelerating EMR initiative in the country

cs.CY↗

arXiv2015

Brain Computer Interfaces for Mobile Apps: State-of-the-art and Future Directions

In recent times, there have been significant advancements in utilizing the sensing capabilities of mobile devices for developing applications. The primary objective has been to enhance the way a user interacts with the application by making it effortless and convenient. This paper explores the capabilities of using Brain Computer Interfaces (BCI), an evolving subset of Human Computer Interaction (HCI) paradigms, to control mobile devices. We present a comprehensive survey of the state-of-the-art in this area, discussing the challenges and limitations in using BCI for mobile applications. Further we propose possible modalities that in future can benefit with BCI applications. This paper consolidates research directions being pursued in this domain, and draws conclusions on feasibility and benefits of using BCI systems effectively augmented to the mobile application development domain.

cs.HC↗

arXiv2015

Benchmarking KAZE and MCM for Multiclass Classification

In this paper, we propose a novel approach for feature generation by appropriately fusing KAZE and SIFT features. We then use this feature set along with Minimal Complexity Machine(MCM) for object classification. We show that KAZE and SIFT features are complementary. Experimental results indicate that an elementary integration of these techniques can outperform the state-of-the-art approaches.

cs.CV↗

arXiv2015

SIFT Vs SURF: Quantifying the Variation in Transformations

This paper studies the robustness of SIFT and SURF against different image transforms (rigid body, similarity, affine and projective) by quantitatively analyzing the variations in the extent of transformations. Previous studies have been comparing the two techniques on absolute transformations rather than the specific amount of deformation caused by the transformation. The paper establishes an exhaustive empirical analysis of such deformations and matching capability of SIFT and SURF with variations in matching parameters and the amount of tolerance. This is helpful in choosing the specific use case for applying these techniques.

cs.CV↗

arXiv2009

Simulating reachability using first-order logic with applications to verification of linked data structures

This paper shows how to harness existing theorem provers for first-order logic to automatically verify safety properties of imperative programs that perform dynamic storage allocation and destructive updating of pointer-valued structure fields. One of the main obstacles is specifying and proving the (absence) of reachability properties among dynamically allocated cells. The main technical contributions are methods for simulating reachability in a conservative way using first-order formulas--the formulas describe a superset of the set of program states that would be specified if one had a precise way to express reachability. These methods are employed for semi-automatic program verification (i.e., using programmer-supplied loop invariants) on programs such as mark-and-sweep garbage collection and destructive reversal of a singly linked list. (The mark-and-sweep example has been previously reported as being beyond the capabilities of ESC/Java.)

cs.LO↗