Search Results for author:
Found 10 papers, 4 papers with code
Adaptive Margin Diversity Regularizer for handling Data Imbalance in Zero-Shot SBIR
Extensive experiments and analysis justifies the effectiveness of the proposed AMDReg for mitigating the effect of data imbalance for generalization to unseen classes in ZS-SBIR.
Domain Generalisation via Imprecise Learning
Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e. g., optimising the average-case risk, worst-case risk, or interpolations thereof.
Fast Adaptive Test-Time Defense with Robust Features
Adaptive test-time defenses are used to improve the robustness of deep neural networks to adversarial examples.
Pred&Guide: Labeled Target Class Prediction for Guiding Semi-Supervised Domain Adaptation
Here, we propose a novel framework, Pred&Guide, which leverages the inconsistency between the predicted and the actual class labels of the few labeled target examples to effectively guide the domain adaptation in a semi-supervised setting.
Semi-supervised Domain Adaptation
Unsupervised Domain Adaptation
Optimal Reservoir Operations using Long Short-Term Memory Network
Although, experiments are run on data from Bhakra Dam Reservoir in India, LSTM model, and anomaly detection algorithm are general purpose and can be applied to any basin with minimal changes.
A combinatorial statistic for labeled threshold graphs
Consider the collection of hyperplanes in $\mathbb{R}^n$ whose defining equations are given by $\{x_i + x_j = 0\mid 1\leq i<j\leq n\}$.
Combinatorics 52C35, 05C30, 11B73
Counting regions of the boxed threshold arrangement
We call it the \emph{boxed threshold arrangement} since we show that the bounded regions of this arrangement are contained in an $n$-cube and are in one-to-one correspondence with the labeled threshold graphs on $n$ vertices.
Combinatorics 52C35, 32S22, 05C30, 11B68
Vertex decomposability of complexes associated to forests
In this article, we discuss the vertex decomposability of three well-studied simplicial complexes associated to forests.
Combinatorics 05C05, 05E45, 55P10, 55U10
Self-Supervision based Task-Specific Image Collection Summarization
Successful applications of deep learning (DL) requires large amount of annotated data.
A Gaussian Process Upsampling Model for Improvements in Optical Character Recognition
Optical Character Recognition and extraction is a key tool in the automatic evaluation of documents in a financial context.
Optical Character Recognition
Optical Character Recognition (OCR)
