Search Results for author: Mahesan Niranjan

Found 17 papers, 5 papers with code

Thinking Outside the Box: Orthogonal Approach to Equalizing Protected Attributes

no code implementations21 Nov 2023 Jiahui Liu, Xiaohao Cai, Mahesan Niranjan

There is growing concern that the potential of black box AI may exacerbate health-related disparities and biases such as gender and ethnicity in clinical decision-making.

Attribute Decision Making +1

Depth Insight -- Contribution of Different Features to Indoor Single-image Depth Estimation

no code implementations16 Nov 2023 Yihong Wu, Yuwen Heng, Mahesan Niranjan, Hansung Kim

To this end, in this work, we quantify the relative contributions of the known cues of depth in a monocular depth estimation setting using an indoor scene data set.

Edge Detection Monocular Depth Estimation

IIHT: Medical Report Generation with Image-to-Indicator Hierarchical Transformer

no code implementations10 Aug 2023 Keqiang Fan, Xiaohao Cai, Mahesan Niranjan

The classifier module first extracts image features from the input medical images and produces disease-related indicators with their corresponding states.

Image Captioning Machine Translation +1

GO-LDA: Generalised Optimal Linear Discriminant Analysis

no code implementations23 May 2023 Jiahui Liu, Xiaohao Cai, Mahesan Niranjan

Linear discriminant analysis (LDA) has been a useful tool in pattern recognition and data analysis research and practice.

Do prompt positions really matter?

no code implementations23 May 2023 Junyu Mao, Stuart E. Middleton, Mahesan Niranjan

Prompt-based models have gathered a lot of attention from researchers due to their remarkable advancements in the fields of zero-shot and few-shot learning.

Few-Shot Learning Natural Language Understanding +2

Construction of Minimum Spanning Trees from Financial Returns using Rank Correlation

1 code implementation8 May 2020 Tristan Millington, Mahesan Niranjan

MSTs constructed using these rank methods tend to be more stable and maintain more edges over the dataset than those constructed using Pearson correlation.

Computational Engineering, Finance, and Science Statistical Finance

FMix: Enhancing Mixed Sample Data Augmentation

5 code implementations27 Feb 2020 Ethan Harris, Antonia Marcu, Matthew Painter, Mahesan Niranjan, Adam Prügel-Bennett, Jonathon Hare

Finally, we show that a consequence of the difference between interpolating MSDA such as MixUp and masking MSDA such as FMix is that the two can be combined to improve performance even further.

Data Augmentation Image Classification

A Variational Autoencoder for Probabilistic Non-Negative Matrix Factorisation

no code implementations ICLR 2019 Steven Squires, Adam Prügel Bennett, Mahesan Niranjan

We design a network which can perform non-negative matrix factorisation (NMF) and add in aspects of a VAE to make the coefficients of the latent space probabilistic.

Time Series Time Series Analysis

A numerical measure of the instability of Mapper-type algorithms

1 code implementation4 Jun 2019 Francisco Belchí, Jacek Brodzki, Matthew Burfitt, Mahesan Niranjan

We define an intrinsic notion of Mapper instability that measures the variability of the output as a function of the choice of parameters required to construct a Mapper output.

Clustering Vocal Bursts Type Prediction

Minimum description length as an objective function for non-negative matrix factorization

no code implementations5 Feb 2019 Steven Squires, Adam Prugel Bennett, Mahesan Niranjan

Non-negative matrix factorization (NMF) is a dimensionality reduction technique which tends to produce a sparse representation of data.

Dimensionality Reduction

Parameter Estimation in Computational Biology by Approximate Bayesian Computation coupled with Sensitivity Analysis

1 code implementation28 Apr 2017 Xin Liu, Mahesan Niranjan

We address the problem of parameter estimation in models of systems biology from noisy observations.

Enriching Texture Analysis with Semantic Data

no code implementations CVPR 2013 Tim Matthews, Mark S. Nixon, Mahesan Niranjan

Low-level visual features used by existing texture descriptors are then assessed in terms of their correspondence to the semantic space.

feature selection Retrieval +2

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