Search Results for author: Tirtharaj Dash

Found 24 papers, 7 papers with code

Domain-Specific Pre-training Improves Confidence in Whole Slide Image Classification

1 code implementation20 Feb 2023 Soham Rohit Chitnis, Sidong Liu, Tirtharaj Dash, Tanmay Tulsidas Verlekar, Antonio Di Ieva, Shlomo Berkovsky, Lovekesh Vig, Ashwin Srinivasan

To investigate the effect of domain-specific pre-training, we considered the current state-of-the-art multiple-instance learning models, 1) CLAM, an attention-based model, and 2) TransMIL, a self-attention-based model, and evaluated the models' confidence and predictive performance in detecting primary brain tumors - gliomas.

Image Classification Multiple Instance Learning +1

Calibrating Deep Neural Networks using Explicit Regularisation and Dynamic Data Pruning

no code implementations20 Dec 2022 Ramya Hebbalaguppe, Rishabh Patra, Tirtharaj Dash, Gautam Shroff, Lovekesh Vig

Contemporary model calibration techniques mitigate the problem of overconfident predictions by pushing down the confidence of the winning class while increasing the confidence of the remaining classes across all test samples.

Image Classification

Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spaces

no code implementations19 Sep 2022 Vishwa Shah, Aditya Sharma, Gautam Shroff, Lovekesh Vig, Tirtharaj Dash, Ashwin Srinivasan

However, connectionist models struggle to include explicit domain knowledge for deductive reasoning.

Composition of Relational Features with an Application to Explaining Black-Box Predictors

1 code implementation1 Jun 2022 Ashwin Srinivasan, A Baskar, Tirtharaj Dash, Devanshu Shah

Using a notion of explanations based on the compositional structure of features in a CRM, we provide empirical evidence on synthetic data of the ability to identify appropriate explanations; and demonstrate the use of CRMs as 'explanation machines' for black-box models that do not provide explanations for their predictions.

Inductive logic programming

Solving Visual Analogies Using Neural Algorithmic Reasoning

no code implementations19 Nov 2021 Atharv Sonwane, Gautam Shroff, Lovekesh Vig, Ashwin Srinivasan, Tirtharaj Dash

We consider a class of visual analogical reasoning problems that involve discovering the sequence of transformations by which pairs of input/output images are related, so as to analogously transform future inputs.

Program Synthesis Visual Analogies

A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks

no code implementations21 Jul 2021 Tirtharaj Dash, Sharad Chitlangia, Aditya Ahuja, Ashwin Srinivasan

We present a survey of ways in which existing scientific knowledge are included when constructing models with neural networks.

Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment

1 code implementation22 May 2021 Tirtharaj Dash, Ashwin Srinivasan, A Baskar

We also provide experimental evidence comparing BotGNNs favourably to multi-layer perceptrons (MLPs) that use features representing a "propositionalised" form of the background knowledge; and BotGNNs to a standard ILP based on the use of most-specific clauses.

Inductive logic programming

Superpixel-based Knowledge Infusion in Deep Neural Networks for Image Classification

1 code implementation20 May 2021 Gunjan Chhablani, Abheesht Sharma, Harshit Pandey, Tirtharaj Dash

Our experiments are extensive, and we evaluate the predictive performance of our proposed hybrid vision model on seven different image classification datasets from a variety of domains such as digit and object recognition, biometrics, medical imaging.

Face Recognition Image Classification +2

Incorporating Domain Knowledge into Deep Neural Networks

no code implementations27 Feb 2021 Tirtharaj Dash, Sharad Chitlangia, Aditya Ahuja, Ashwin Srinivasan

We present a survey of ways in which domain-knowledge has been included when constructing models with neural networks.

Constructing and Evaluating an Explainable Model for COVID-19 Diagnosis from Chest X-rays

no code implementations19 Dec 2020 Rishab Khincha, Soundarya Krishnan, Tirtharaj Dash, Lovekesh Vig, Ashwin Srinivasan

In this paper, deep neural networks are used to extract domain-specific features(morphological features like ground-glass opacity and disease indications like pneumonia) directly from the image data.

COVID-19 Diagnosis

Incorporating Symbolic Domain Knowledge into Graph Neural Networks

2 code implementations23 Oct 2020 Tirtharaj Dash, Ashwin Srinivasan, Lovekesh Vig

These kinds of problems have been addressed effectively in the past by Inductive Logic Programming (ILP), by virtue of 2 important characteristics: (a) The use of a representation language that easily captures the relation encoded in graph-structured data, and (b) The inclusion of prior information encoded as domain-specific relations, that can alleviate problems of data scarcity, and construct new relations.

Inductive logic programming

A study on the use of Boundary Equilibrium GAN for Approximate Frontalization of Unconstrained Faces to aid in Surveillance

no code implementations14 Sep 2018 Wazeer Zulfikar, Sebastin Santy, Sahith Dambekodi, Tirtharaj Dash

Specifically, the present work is a comprehensive study on the implementation of an auto-encoder based Boundary Equilibrium GAN (BEGAN) to generate frontal faces using an interpolation of a side view face and its mirrored view.

Face Generation Generative Adversarial Network

Reliable Evaluation of Neural Network for Multiclass Classification of Real-world Data

no code implementations30 Nov 2016 Siddharth Dinesh, Tirtharaj Dash

The results that are obtained for different parameters for each of the dataset could demonstrate interesting findings to support the usability of these set of performance evaluation parameters.

General Classification

A Fuzzy MLP Approach for Non-linear Pattern Classification

no code implementations19 Sep 2015 Tirtharaj Dash, H. S. Behera

Pattern classification using multilayer perceptron (MLP) trained with back propagation learning becomes much complex with increase in number of layers, number of nodes and number of epochs and ultimate increases computational time [31].

Classification Decision Making +1

A Novel Approach for Intelligent Robot Path Planning

no code implementations19 Jun 2013 Tirtharaj Dash, Goutam Mishra, Tanistha Nayak

Path planning of Robot is one of the challenging fields in the area of Robotics research.

Robotics

Non-Correlated Character Recognition using Artificial Neural Network

no code implementations19 Jun 2013 Tirtharaj Dash, Tanistha Nayak

Fifty-two sets of English alphabets are used to train the ANN and test the network.

Solution to Quadratic Equation Using Genetic Algorithm

no code implementations19 Jun 2013 Tanistha Nayak, Tirtharaj Dash

A novel approach for solving Quadratic Equation based on Genetic Algorithms (GAs) is presented.

Time Efficient Approach To Offline Hand Written Character Recognition Using Associative Memory Net

no code implementations19 Jun 2013 Tirtharaj Dash

The developed network consumes 3. 57 sec (average) in Serial implementation and 1. 16 sec (average) in Parallel implementation using OpenMP.

English Character Recognition using Artificial Neural Network

no code implementations19 Jun 2013 Tirtharaj Dash, Tanistha Nayak

This work focuses on development of a Offline Hand Written English Character Recognition algorithm based on Artificial Neural Network (ANN).

Cannot find the paper you are looking for? You can Submit a new open access paper.