16 citations · 79 across the 25 of their papers we have counts for
27 papers
GeoMER: A Joint Euclidean-Hyperbolic Geometry Framework for Multimodal Emotion Recognition
Ting Zhu, Huizhi Liang, Boguslaw Obara +2
Multimodal Emotion Recognition (MER) aims to understand human emotions by integrating information from multiple modalities such as speech and text. Psychological studies suggest th…
Personalized Federated Sparse Adaptation of Time-Series Foundation Models
Priyanka Nihalchandani, Naman Srivastava, Varun Ojha +1
Federated adaptation of time-series foundation models (TSFMs) is attractive for building energy forecasting because meter data are private, distributed, and highly non-IID. However…
Hyperbolic Manifold Constrained Tabular Neural Network
Tian Li, Lucy Robinson, Varun Ojha +1
Tabular prediction is central to a wide range of real-world applications. Tabular data typically contain heterogeneous features as well as rich and complex relational information t…
Systematic Characterization of Minimal Deep Learning Architectures: A Unified Analysis of Convergence, Pruning, and Quantization
Ziwei Zheng, Huizhi Liang, Vaclav Snasel +4
Deep learning networks excel at classification, yet identifying minimal architectures that reliably solve a task remains challenging. We present a computational methodology for sys…
AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction
Ruikai Li, Xinrun Li, Mengwei Xie +12
Online High-Definition (HD) map construction is pivotal for autonomous driving. While recent approaches leverage historical temporal fusion to improve performance, we identify a cr…
Learning Global Representation from Queries for Vectorized HD Map Construction
Shoumeng Qiu, Xinrun Li, Yang Long +3
The online construction of vectorized high-definition (HD) maps is a cornerstone of modern autonomous driving systems. State-of-the-art approaches, particularly those based on the…
RegMix: Adversarial Mutual and Generalization Regularization for Enhancing DNN Robustness
Zhenyu Liu, Varun Ojha
Adversarial training is the most effective defense against adversarial attacks. The effectiveness of the adversarial attacks has been on the design of its loss function and regular…
Deep Learning-Assisted Detection of Sarcopenia in Cross-Sectional Computed Tomography Imaging
Manish Bhardwaj, Huizhi Liang, Ashwin Sivaharan +4
Sarcopenia is a progressive loss of muscle mass and function linked to poor surgical outcomes such as prolonged hospital stays, impaired mobility, and increased mortality. Although…
AdaGAT: Adaptive Guidance Adversarial Training for the Robustness of Deep Neural Networks
Zhenyu Liu, Huizhi Liang, Xinrun Li +2
Adversarial distillation (AD) is a knowledge distillation technique that facilitates the transfer of robustness from teacher deep neural network (DNN) models to lightweight target…
D2R: dual regularization loss with collaborative adversarial generation for model robustness
Zhenyu Liu, Huizhi Liang, Rajiv Ranjan +3
The robustness of Deep Neural Network models is crucial for defending models against adversarial attacks. Recent defense methods have employed collaborative learning frameworks to…
D2Fusion: Dual-domain Fusion with Feature Superposition for Deepfake Detection
Xueqi Qiu, Xingyu Miao, Fan Wan +5
Deepfake detection is crucial for curbing the harm it causes to society. However, current Deepfake detection methods fail to thoroughly explore artifact information across differen…
3D Modeling and Automated Measurement of Concrete Cracks via Segment Anything Refinement and Visual Inertial LiDAR Fusion
Pengru Deng, Jiapeng Yao, Chun Li +4
Visual-Spatial Systems has become increasingly essential in concrete crack inspection. However, existing methods often lacks adaptability to diverse scenarios, exhibits limited rob…
Exemplar-condensed Federated Class-incremental Learning
Rui Sun, Yumin Zhang, Varun Ojha +4
We propose Exemplar-Condensed federated class-incremental learning (ECoral) to distil the training characteristics of real images from streaming data into informative rehearsal exe…
Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
Zhenyu Liu, Haoran Duan, Huizhi Liang +5
Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectur…
On Learnable Parameters of Optimal and Suboptimal Deep Learning Models
Ziwei Zheng, Huizhi Liang, Vaclav Snasel +4
We scrutinize the structural and operational aspects of deep learning models, particularly focusing on the nuances of learnable parameters (weight) statistics, distribution, node i…
Wearable-based behaviour interpolation for semi-supervised human activity recognition
Haoran Duan, Shidong Wang, Varun Ojha +5
While traditional feature engineering for Human Activity Recognition (HAR) involves a trial-anderror process, deep learning has emerged as a preferred method for high-level represe…
Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching
Xingyu Miao, Haoran Duan, Varun Ojha +4
In this work, we propose a novel Trajectory Score Matching (TSM) method that aims to solve the pseudo ground truth inconsistency problem caused by the accumulated error in Interval…
Rehearsal-free Federated Domain-incremental Learning
Rui Sun, Haoran Duan, Jiahua Dong +3
We introduce a rehearsal-free federated domain incremental learning framework, RefFiL, based on a global prompt-sharing paradigm to alleviate catastrophic forgetting challenges in…
Fine-tuning Large Language Models for Multigenerator, Multidomain, and Multilingual Machine-Generated Text Detection
Feng Xiong, Thanet Markchom, Ziwei Zheng +3
SemEval-2024 Task 8 introduces the challenge of identifying machine-generated texts from diverse Large Language Models (LLMs) in various languages and domains. The task comprises t…
Fragility, Robustness and Antifragility in Deep Learning
Chandresh Pravin, Ivan Martino, Giuseppe Nicosia +1
We propose a systematic analysis of deep neural networks (DNNs) based on a signal processing technique for network parameter removal, in the form of synaptic filters that identifie…
Adaptive search space decomposition method for pre- and post- buckling analyses of space truss structures
Varun Ojha, Bartolomeo Panto, Giuseppe Nicosia
The paper proposes a novel adaptive search space decomposition method and a novel gradient-free optimization-based formulation for the pre- and post-buckling analyses of space trus…
Assessing Ranking and Effectiveness of Evolutionary Algorithm Hyperparameters Using Global Sensitivity Analysis Methodologies
Varun Ojha, Jon Timmis, Giuseppe Nicosia
We present a comprehensive global sensitivity analysis of two single-objective and two multi-objective state-of-the-art global optimization evolutionary algorithms as an algorithm…
Transfer Learning for Instance Segmentation of Waste Bottles using Mask R-CNN Algorithm
Punitha Jaikumar, Remy Vandaele, Varun Ojha
This paper proposes a methodological approach with a transfer learning scheme for plastic waste bottle detection and instance segmentation using the \textit{mask region proposal co…
Backpropagation Neural Tree
Varun Ojha, Giuseppe Nicosia
We propose a novel algorithm called Backpropagation Neural Tree (BNeuralT), which is a stochastic computational dendritic tree. BNeuralT takes random repeated inputs through its le…