In this paper, we explore a novel model reusing task tailored for graph neural networks (GNNs), termed as" deep graph reprogramming". We strive to reprogram a pre-trained GNN …
A Chen, Y Yao, PY Chen… - Proceedings of the …, 2023 - openaccess.thecvf.com
We revisit and advance visual prompting (VP), an input prompting technique for vision tasks. VP can reprogram a fixed, pre-trained source model to accomplish downstream tasks in the …
Despite a surge of recent advances in promoting machine Learning (ML) fairness, the existing mainstream approaches mostly require training or finetuning the entire weights of …
A Qammar, H Wang, J Ding, A Naouri… - arXiv preprint arXiv …, 2023 - arxiv.org
Chatbots shifted from rule-based to artificial intelligence techniques and gained traction in medicine, shopping, customer services, food delivery, education, and research. OpenAI …
In this paper, we study the problem of temporal video grounding (TVG), which aims to predict the starting/ending time points of moments described by a text sentence within a long …
PY Chen - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
In data-rich domains such as vision, language, and speech, deep learning prevails to deliver high-performance task-specific models and can even learn general task-agnostic …
In this work, we leverage visual prompting (VP) to improve adversarial robustness of a fixed, pre-trained model at test time. Compared to conventional adversarial defenses, VP allows …
Massive data is often considered essential for deep learning applications, but it also incurs significant computational and infrastructural costs. Therefore, dataset pruning (DP) has …
M Kim, HI Kim, YM Ro - arXiv preprint arXiv:2302.08102, 2023 - arxiv.org
Visual Speech Recognition (VSR) aims to infer speech into text depending on lip movements alone. As it focuses on visual information to model the speech, its performance …