arXiv subjects

Ashish Mishra

Publications and source records attributed to Ashish Mishra.

34 records · Page 2Linked to original sources

arXiv2020

EMPOL: an EMCCD based optical imaging polarimeter

An Andor 1K $\times$ 1K EMCCD detector has been used to develop an optical imaging polarimeter for use at the Cassegrain focus of 1.2 m telescope of PRL. The optics is derived from an older single-element detector instrument and consists of a rotating half-wave plate as modulator and a Foster prism as an analyser. The field of view of the instrument is 3 $\times$ 3 sq arcmin. We describe the instrument and the observational methodology in this document. Extensive observations have been carried out with this instrument covering a large variety of sources e.g. near-Earth asteroids, comets, Lynds dark nebulae, open clusters and AGN such as blazars. In the current communication, we discuss some results from the initial calibration runs while the other results will be presented elsewhere.

astro-ph.IM↗

arXiv2020

Towards Zero-Shot Learning with Fewer Seen Class Examples

We present a meta-learning based generative model for zero-shot learning (ZSL) towards a challenging setting when the number of training examples from each \emph{seen} class is very few. This setup contrasts with the conventional ZSL approaches, where training typically assumes the availability of a sufficiently large number of training examples from each of the seen classes. The proposed approach leverages meta-learning to train a deep generative model that integrates variational autoencoder and generative adversarial networks. We propose a novel task distribution where meta-train and meta-validation classes are disjoint to simulate the ZSL behaviour in training. Once trained, the model can generate synthetic examples from seen and unseen classes. Synthesize samples can then be used to train the ZSL framework in a supervised manner. The meta-learner enables our model to generates high-fidelity samples using only a small number of training examples from seen classes. We conduct extensive experiments and ablation studies on four benchmark datasets of ZSL and observe that the proposed model outperforms state-of-the-art approaches by a significant margin when the number of examples per seen class is very small.

cs.CV↗

arXiv2020

Fuzzy Unique Image Transformation: Defense Against Adversarial Attacks On Deep COVID-19 Models

Early identification of COVID-19 using a deep model trained on Chest X-Ray and CT images has gained considerable attention from researchers to speed up the process of identification of active COVID-19 cases. These deep models act as an aid to hospitals that suffer from the unavailability of specialists or radiologists, specifically in remote areas. Various deep models have been proposed to detect the COVID-19 cases, but few works have been performed to prevent the deep models against adversarial attacks capable of fooling the deep model by using a small perturbation in image pixels. This paper presents an evaluation of the performance of deep COVID-19 models against adversarial attacks. Also, it proposes an efficient yet effective Fuzzy Unique Image Transformation (FUIT) technique that downsamples the image pixels into an interval. The images obtained after the FUIT transformation are further utilized for training the secure deep model that preserves high accuracy of the diagnosis of COVID-19 cases and provides reliable defense against the adversarial attacks. The experiments and results show the proposed model prevents the deep model against the six adversarial attacks and maintains high accuracy to classify the COVID-19 cases from the Chest X-Ray image and CT image Datasets. The results also recommend that a careful inspection is required before practically applying the deep models to diagnose the COVID-19 cases.

eess.IV↗

arXiv2020

Jucys-Murphy elements of partition algebras for the rook monoid

Kudryavtseva and Mazorchuk exhibited Schur-Weyl duality between the rook monoid algebra $\mathbb{C}R_n$ and the subalgebra $\mathbb{C}I_k$ of the partition algebra $\mathbb{C} A_k(n)$ acting on $(\mathbb{C}^n)^{\otimes k}$. In this paper, we consider a subalgebra $\mathbb{C}I_{k+\frac{1}{2}}$ of $\mathbb{C} I_{k+1}$ such that there is Schur-Weyl duality between the actions of $\mathbb{C} R_{n-1}$ and $\mathbb{C} I_{k+\frac{1}{2}}$ on $(\mathbb{C}^n)^{\otimes k}$. This paper studies the representation theory of partition algebras $\mathbb{C}I_k$ and $\mathbb{C}I_{k+\frac{1}{2}}$ for rook monoids inductively by considering the multiplicity free tower $$\mathbb{C} I_1\subset \mathbb{C} I_{\frac{3}{2}}\subset \mathbb{C} I_{2}\subset \cdots\subset \mathbb{C} I_{k}\subset \mathbb{C} I_{k+\frac{1}{2}}\subset\cdots.$$ Furthermore, this inductive approach is established as a spectral approach by describing the Jucys-Murphy elements and their actions on the canonical Gelfand-Tsetlin bases, determined by the aforementioned multiplicity free tower, of irreducible representations of $\mathbb{C} I_k$ and $\mathbb{C} I_{k+\frac{1}{2}}$. Also, we describe the Jucys-Murphy elements of $\mathbb{C} R_n$ which play a central role in the demonstration of the actions of Jucys-Murphy elements of $\mathbb{C} I_k$ and $\mathbb{C}I_{k+\frac{1}{2}}$.

math.RT↗

arXiv2020

Stacked Adversarial Network for Zero-Shot Sketch based Image Retrieval

Conventional approaches to Sketch-Based Image Retrieval (SBIR) assume that the data of all the classes are available during training. The assumption may not always be practical since the data of a few classes may be unavailable, or the classes may not appear at the time of training. Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) relaxes this constraint and allows the algorithm to handle previously unseen classes during the test. This paper proposes a generative approach based on the Stacked Adversarial Network (SAN) and the advantage of Siamese Network (SN) for ZS-SBIR. While SAN generates a high-quality sample, SN learns a better distance metric compared to that of the nearest neighbor search. The capability of the generative model to synthesize image features based on the sketch reduces the SBIR problem to that of an image-to-image retrieval problem. We evaluate the efficacy of our proposed approach on TU-Berlin, and Sketchy database in both standard ZSL and generalized ZSL setting. The proposed method yields a significant improvement in standard ZSL as well as in a more challenging generalized ZSL setting (GZSL) for SBIR.

cs.CV↗

arXiv2019

Generative Model for Zero-Shot Sketch-Based Image Retrieval

We present a probabilistic model for Sketch-Based Image Retrieval (SBIR) where, at retrieval time, we are given sketches from novel classes, that were not present at training time. Existing SBIR methods, most of which rely on learning class-wise correspondences between sketches and images, typically work well only for previously seen sketch classes, and result in poor retrieval performance on novel classes. To address this, we propose a generative model that learns to generate images, conditioned on a given novel class sketch. This enables us to reduce the SBIR problem to a standard image-to-image search problem. Our model is based on an inverse auto-regressive flow based variational autoencoder, with a feedback mechanism to ensure robust image generation. We evaluate our model on two very challenging datasets, Sketchy, and TU Berlin, with novel train-test split. The proposed approach significantly outperforms various baselines on both the datasets.

cs.CV↗

arXiv2018

On representation theory of partition algebras for complex reflection groups

This paper defines the partition algebra for complex reflection group $G(r,p,n)$ acting on $k$-fold tensor product $(\mathbb{C}^n)^{\otimes k}$, where $\mathbb{C}^n$ is the reflection representation of $G(r,p,n)$. A basis of the centralizer algebra of this action of $G(r,p,n)$ was given by Tanabe and for $p =1$, the corresponding partition algebra was studied by Orellana. We also establish a subalgebra as partition algebra of a subgroup of $G(r,p,n)$ acting on $(\mathbb{C}^n)^{\otimes k}$. We call these algebras as Tanabe algebras. The aim of this paper is to study representation theory of Tanabe algebras: parametrization of their irreducible modules, and construction of Bratteli diagram for the tower of Tanabe algebras. We conclude the paper by giving Jucys-Murphy elements of Tanabe algebras and their actions on the Gelfand-Tsetlin basis, determined by this multiplicity free tower, of irreducible modules.

math.RT↗

arXiv2018

A Zero-Shot Framework for Sketch-based Image Retrieval

Sketch-based image retrieval (SBIR) is the task of retrieving images from a natural image database that correspond to a given hand-drawn sketch. Ideally, an SBIR model should learn to associate components in the sketch (say, feet, tail, etc.) with the corresponding components in the image having similar shape characteristics. However, current evaluation methods simply focus only on coarse-grained evaluation where the focus is on retrieving images which belong to the same class as the sketch but not necessarily having the same shape characteristics as in the sketch. As a result, existing methods simply learn to associate sketches with classes seen during training and hence fail to generalize to unseen classes. In this paper, we propose a new benchmark for zero-shot SBIR where the model is evaluated in novel classes that are not seen during training. We show through extensive experiments that existing models for SBIR that are trained in a discriminative setting learn only class specific mappings and fail to generalize to the proposed zero-shot setting. To circumvent this, we propose a generative approach for the SBIR task by proposing deep conditional generative models that take the sketch as an input and fill the missing information stochastically. Experiments on this new benchmark created from the "Sketchy" dataset, which is a large-scale database of sketch-photo pairs demonstrate that the performance of these generative models is significantly better than several state-of-the-art approaches in the proposed zero-shot framework of the coarse-grained SBIR task.

cs.CV↗

arXiv2018

Generalized Zero-Shot Learning via Synthesized Examples

We present a generative framework for generalized zero-shot learning where the training and test classes are not necessarily disjoint. Built upon a variational autoencoder based architecture, consisting of a probabilistic encoder and a probabilistic conditional decoder, our model can generate novel exemplars from seen/unseen classes, given their respective class attributes. These exemplars can subsequently be used to train any off-the-shelf classification model. One of the key aspects of our encoder-decoder architecture is a feedback-driven mechanism in which a discriminator (a multivariate regressor) learns to map the generated exemplars to the corresponding class attribute vectors, leading to an improved generator. Our model's ability to generate and leverage examples from unseen classes to train the classification model naturally helps to mitigate the bias towards predicting seen classes in generalized zero-shot learning settings. Through a comprehensive set of experiments, we show that our model outperforms several state-of-the-art methods, on several benchmark datasets, for both standard as well as generalized zero-shot learning.

cs.LG↗

arXiv2018

A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoders

Zero shot learning in Image Classification refers to the setting where images from some novel classes are absent in the training data but other information such as natural language descriptions or attribute vectors of the classes are available. This setting is important in the real world since one may not be able to obtain images of all the possible classes at training. While previous approaches have tried to model the relationship between the class attribute space and the image space via some kind of a transfer function in order to model the image space correspondingly to an unseen class, we take a different approach and try to generate the samples from the given attributes, using a conditional variational autoencoder, and use the generated samples for classification of the unseen classes. By extensive testing on four benchmark datasets, we show that our model outperforms the state of the art, particularly in the more realistic generalized setting, where the training classes can also appear at the test time along with the novel classes.

cs.CV↗

arXiv2018

A Generative Approach to Zero-Shot and Few-Shot Action Recognition

We present a generative framework for zero-shot action recognition where some of the possible action classes do not occur in the training data. Our approach is based on modeling each action class using a probability distribution whose parameters are functions of the attribute vector representing that action class. In particular, we assume that the distribution parameters for any action class in the visual space can be expressed as a linear combination of a set of basis vectors where the combination weights are given by the attributes of the action class. These basis vectors can be learned solely using labeled data from the known (i.e., previously seen) action classes, and can then be used to predict the parameters of the probability distributions of unseen action classes. We consider two settings: (1) Inductive setting, where we use only the labeled examples of the seen action classes to predict the unseen action class parameters; and (2) Transductive setting which further leverages unlabeled data from the unseen action classes. Our framework also naturally extends to few-shot action recognition where a few labeled examples from unseen classes are available. Our experiments on benchmark datasets (UCF101, HMDB51 and Olympic) show significant performance improvements as compared to various baselines, in both standard zero-shot (disjoint seen and unseen classes) and generalized zero-shot learning settings.

cs.CV↗

arXiv2017

Presburger-Definable Parameterized Typestates

Typestates are good at capturing dynamic states of a program as compared to normal types that can capture static structural properties of data and program. Although useful, typestates are suitable only for specifying and verifying program properties defined using finite-state abstractions. Many useful dynamic properties of programs are not finite-state definable. To address these issues, we introduce parameterized typestates (p-typestates). p-typestates associate a logical property with each state of regular typestate, thereby allowing specification of properties beyond finite-state abstractions. We present a dependent type system to express and verify p-typestate properties and a typestate-oriented core programming language incorporating these dependent types. Automatic inductive type-checking of p-typestate properties usually requires a programmer to provide loop invariants as annotations. Here we propose a way to calculate loop invariants automatically, using loop acceleration techniques for Presburger definable transition systems. \keywords{Programming Languages, Typestates, Dependent Types, Non-Regular Program Properties, Verification, Loop Invariants}

cs.PL↗

arXiv2017

Beyond-Regular Typestate

We present an extension for regular typestates, called Beyond- Regular Typestate(BR-Typestate), which is expressive enough to model non-regular properties of programs and protocols over data. We model the BR-Typestate system over a dependently typed, state based, impera- tive core language, and we prove its soundness and tractability. We have implemented a prototype typechecker for the language, and we show how several important, real world non-regular properties of programs and protocols can be verified.

cs.PL↗

arXiv2016

Bi-modal First Impressions Recognition using Temporally Ordered Deep Audio and Stochastic Visual Features

We propose a novel approach for First Impressions Recognition in terms of the Big Five personality-traits from short videos. The Big Five personality traits is a model to describe human personality using five broad categories: Extraversion, Agreeableness, Conscientiousness, Neuroticism and Openness. We train two bi-modal end-to-end deep neural network architectures using temporally ordered audio and novel stochastic visual features from few frames, without over-fitting. We empirically show that the trained models perform exceptionally well, even after training from a small sub-portions of inputs. Our method is evaluated in ChaLearn LAP 2016 Apparent Personality Analysis (APA) competition using ChaLearn LAP APA2016 dataset and achieved excellent performance.

cs.CV↗

arXiv2015

On the representation theory of $G\sim S_n$

In the Vershik-Okounkov approach to the complex irreducible representations of $S_n$ and $G\sim S_n$ we parametrize the irreducible representations and their bases by spectral objects rather than combinatorial objects and then, at the end, give a bijection between the spectral and combinatorial objects. The fundamental ideas are similar in both cases but there are additional technicalities involved in the $G\sim S_n$ case. This was carried out by Pushkarev. The present work gives a fully detailed exposition of Pushkarev's theory. For the most part we follow the original but our definition of a Gelfand-Tsetlin subspace, based on a multiplicity free chain of subgroups, is slightly different and leads to a more natural development of the theory. We also work out in detail an example, the generalized Johnson scheme, from this viewpoint.

math.CO↗

arXiv2014

Wreath product action on generalized Boolean algebras

Let G be a finite group acting on the finite set X such that the corresponding (complex) permutation representation is multiplicity free. There is a natural rank and order preserving action of the wreath product G~S_n on the generalized Boolean algebra B_X(n). We explicitly block diagonalize the commutant of this action.

math.RT↗