14 citations · 125 across the 88 of their papers we have counts for
19 papers · 1 filter
Class-Prototype Conditional Diffusion Model with Gradient Projection for Continual Learning
Khanh Doan, Quyen Tran, Tung Lam Tran +3
Mitigating catastrophic forgetting is a key hurdle in continual learning. Deep Generative Replay (GR) provides techniques focused on generating samples from prior tasks to enhance…
KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All
Quyen Tran, Hoang Phan, Lam Tran +4
Drawing inspiration from prompt tuning techniques applied to Large Language Models, recent methods based on pre-trained ViT networks have achieved remarkable results in the field o…
Generalization Bounds for Robust Contrastive Learning: From Theory to Practice
Ngoc N. Tran, Lam Tran, Hoang Phan +5
Contrastive Learning first extracts features from unlabeled data, followed by linear probing with labeled data. Adversarial Contrastive Learning (ACL) integrates Adversarial Traini…
Systematic Assessment of Factual Knowledge in Large Language Models
Linhao Luo, Thuy-Trang Vu, Dinh Phung +1
Previous studies have relied on existing question-answering benchmarks to evaluate the knowledge stored in large language models (LLMs). However, this approach has limitations rega…
Cross-adversarial local distribution regularization for semi-supervised medical image segmentation
Thanh Nguyen-Duc, Trung Le, Roland Bammer +3
Medical semi-supervised segmentation is a technique where a model is trained to segment objects of interest in medical images with limited annotated data. Existing semi-supervised…
NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation
Minh-Tuan Tran, Trung Le, Xuan-May Le +3
Data-Free Knowledge Distillation (DFKD) has made significant recent strides by transferring knowledge from a teacher neural network to a student neural network without accessing th…
Sharpness-Aware Teleportation on Riemannian Manifolds
Tuan Truong, Hoang-Phi Nguyen, Haocheng Luo +4
Recent studies highlight the effectiveness of flat minima in enhancing generalization, with sharpness-aware minimization (SAM) achieving state-of-the-art performance. Additionally,…
Towards Generalising Neural Topical Representations
Xiaohao Yang, He Zhao, Dinh Phung +1
Topic models have evolved from conventional Bayesian probabilistic models to recent Neural Topic Models (NTMs). Although NTMs have shown promising performance when trained and test…
Optimal Transport Model Distributional Robustness
Van-Anh Nguyen, Trung Le, Anh Tuan Bui +2
Distributional robustness is a promising framework for training deep learning models that are less vulnerable to adversarial examples and data distribution shifts. Previous works h…
Generating Adversarial Examples with Task Oriented Multi-Objective Optimization
Anh Bui, Trung Le, He Zhao +3
Deep learning models, even the-state-of-the-art ones, are highly vulnerable to adversarial examples. Adversarial training is one of the most efficient methods to improve the model'…
Learning to Quantize Vulnerability Patterns and Match to Locate Statement-Level Vulnerabilities
Michael Fu, Trung Le, Van Nguyen +2
Deep learning (DL) models have become increasingly popular in identifying software vulnerabilities. Prior studies found that vulnerabilities across different vulnerable programs ma…
AIBugHunter: A Practical Tool for Predicting, Classifying and Repairing Software Vulnerabilities
Michael Fu, Chakkrit Tantithamthavorn, Trung Le +4
Many ML-based approaches have been proposed to automatically detect, localize, and repair software vulnerabilities. While ML-based methods are more effective than program analysis-…
Sharpness & Shift-Aware Self-Supervised Learning
Ngoc N. Tran, Son Duong, Hoang Phan +3
Self-supervised learning aims to extract meaningful features from unlabeled data for further downstream tasks. In this paper, we consider classification as a downstream task in pha…
Parameter Estimation in DAGs from Incomplete Data via Optimal Transport
Vy Vo, Trung Le, Tung-Long Vuong +3
Estimating the parameters of a probabilistic directed graphical model from incomplete data is a long-standing challenge. This is because, in the presence of latent variables, both…
Active Continual Learning: On Balancing Knowledge Retention and Learnability
Thuy-Trang Vu, Shahram Khadivi, Mahsa Ghorbanali +2
Acquiring new knowledge without forgetting what has been learned in a sequence of tasks is the central focus of continual learning (CL). While tasks arrive sequentially, the traini…
Hyperbolic Geometry in Computer Vision: A Survey
Pengfei Fang, Mehrtash Harandi, Trung Le +1
Hyperbolic geometry, a Riemannian manifold endowed with constant sectional negative curvature, has been considered an alternative embedding space in many learning scenarios, \eg, n…
Vector Quantized Wasserstein Auto-Encoder
Tung-Long Vuong, Trung Le, He Zhao +4
Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks. Inspired by the sem…
Flat Seeking Bayesian Neural Networks
Van-Anh Nguyen, Tung-Long Vuong, Hoang Phan +3
Bayesian Neural Networks (BNNs) provide a probabilistic interpretation for deep learning models by imposing a prior distribution over model parameters and inferring a posterior dis…
Class Enhancement Losses with Pseudo Labels for Zero-shot Semantic Segmentation
Son Duy Dao, Hengcan Shi, Dinh Phung +1
Recent mask proposal models have significantly improved the performance of zero-shot semantic segmentation. However, the use of a `background' embedding during training in these me…