63 citations · 235 across the 69 of their papers we have counts for
12 papers · 1 filter
LaViP:Language-Grounded Visual Prompts
Nilakshan Kunananthaseelan, Jing Zhang, Mehrtash Harandi
We introduce a language-grounded visual prompting method to adapt the visual encoder of vision-language models for downstream tasks. By capitalizing on language integration, we dev…
Continual Test-time Domain Adaptation via Dynamic Sample Selection
Yanshuo Wang, Jie Hong, Ali Cheraghian +4
The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This pape…
Real-time Neonatal Chest Sound Separation using Deep Learning
Yang Yi Poh, Ethan Grooby, Kenneth Tan +6
Auscultation for neonates is a simple and non-invasive method of providing diagnosis for cardiovascular and respiratory disease. Such diagnosis often requires high-quality heart an…
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,…
Hyperbolic Audio-visual Zero-shot Learning
Jie Hong, Zeeshan Hayder, Junlin Han +3
Audio-visual zero-shot learning aims to classify samples consisting of a pair of corresponding audio and video sequences from classes that are not present during training. An analy…
L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space
Kaushik Roy, Peyman Moghadam, Mehrtash Harandi
The performance of a lifelong learning (L3) model degrades when it is trained on a series of tasks, as the geometrical formation of the embedding space changes while learning novel…
Subspace Distillation for Continual Learning
Kaushik Roy, Christian Simon, Peyman Moghadam +1
An ultimate objective in continual learning is to preserve knowledge learned in preceding tasks while learning new tasks. To mitigate forgetting prior knowledge, we propose a novel…
EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos
Ruyi Zha, Xuelian Cheng, Hongdong Li +2
Reconstructing soft tissues from stereo endoscope videos is an essential prerequisite for many medical applications. Previous methods struggle to produce high-quality geometry and…
CL-MRI: Self-Supervised Contrastive Learning to Improve the Accuracy of Undersampled MRI Reconstruction
Mevan Ekanayake, Zhifeng Chen, Mehrtash Harandi +2
In Magnetic Resonance Imaging (MRI), image acquisitions are often undersampled in the measurement domain to accelerate the scanning process, at the expense of image quality. Howeve…
Exploring Data Geometry for Continual Learning
Zhi Gao, Chen Xu, Feng Li +3
Continual learning aims to efficiently learn from a non-stationary stream of data while avoiding forgetting the knowledge of old data. In many practical applications, data complies…
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…