10 citations · 16 across the 10 of their papers we have counts for
10 papers
PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
Zheng Zhao, Clara Vania, Subhradeep Kayal +3
Large language models (LLMs) have advanced conversational AI assistants. However, systematically evaluating how well these assistants apply personalization--adapting to individual…
Hyperbolic Residual Quantization: Discrete Representations for Data with Latent Hierarchies
Piotr Piękos, Subhradeep Kayal, Alexandros Karatzoglou
Hierarchical data arise in countless domains, from biological taxonomies and organizational charts to legal codes and knowledge graphs. Residual Quantization (RQ) is widely used to…
Leveraging Labelled Data Knowledge: A Cooperative Rectification Learning Network for Semi-supervised 3D Medical Image Segmentation
Yanyan Wang, Kechen Song, Yuyuan Liu +3
Semi-supervised 3D medical image segmentation aims to achieve accurate segmentation using few labelled data and numerous unlabelled data. The main challenge in the design of semi-s…
Source Identification: A Self-Supervision Task for Dense Prediction
Shuai Chen, Subhradeep Kayal, Marleen de Bruijne
The paradigm of self-supervision focuses on representation learning from raw data without the need of labor-consuming annotations, which is the main bottleneck of current data-driv…
A Framework for Auditing Multilevel Models using Explainability Methods
Debarati Bhaumik, Diptish Dey, Subhradeep Kayal
Applications of multilevel models usually result in binary classification within groups or hierarchies based on a set of input features. For transparent and ethical applications of…
Unsupervised Sentence-embeddings by Manifold Approximation and Projection
Subhradeep Kayal
The concept of unsupervised universal sentence encoders has gained traction recently, wherein pre-trained models generate effective task-agnostic fixed-dimensional representations…
Revisiting Edge Detection in Convolutional Neural Networks
Minh Le, Subhradeep Kayal
The ability to detect edges is a fundamental attribute necessary to truly capture visual concepts. In this paper, we prove that edges cannot be represented properly in the first co…
Region-of-interest guided Supervoxel Inpainting for Self-supervision
Subhradeep Kayal, Shuai Chen, Marleen de Bruijne
Self-supervised learning has proven to be invaluable in making best use of all of the available data in biomedical image segmentation. One particularly simple and effective mechani…
Spectral Data Augmentation Techniques to quantify Lung Pathology from CT-images
Subhradeep Kayal, Florian Dubost, Harm A. W. M. Tiddens +1
Data augmentation is of paramount importance in biomedical image processing tasks, characterized by inadequate amounts of labelled data, to best use all of the data that is present…
Unsupervised Image Segmentation using the Deffuant-Weisbuch Model from Social Dynamics
Subhradeep Kayal
Unsupervised image segmentation algorithms aim at identifying disjoint homogeneous regions in an image, and have been subject to considerable attention in the machine vision commun…