1 code implementation • 8 Mar 2024 • Thang M. Pham, Peijie Chen, Tin Nguyen, Seunghyun Yoon, Trung Bui, Anh Totti Nguyen
CLIP-based classifiers rely on the prompt containing a {class name} that is known to the text encoder.
no code implementations • 1 Mar 2024 • Tin Nguyen, Lam Pham, Phat Lam, Dat Ngo, Hieu Tang, Alexander Schindler
In this paper, we propose a deep learning based model for Acoustic Anomaly Detection of Machines, the task for detecting abnormal machines by analysing the machine sound.
no code implementations • 29 Jan 2024 • Phat Lam, Lam Pham, Tin Nguyen, Hieu Tang, Seidl Michael, Alexander Schindler
For this reason, the role of sentence embedding is crucial for capturing both the semantic information between words in the sentence and the contextual relationship of sentences within the abstract to provide a comprehensive representation for better classification.
no code implementations • 22 Dec 2023 • Tin Nguyen, Anh Nguyen
Training CNNs and ViTs with habitat-augmented data results in an improvement of up to +0. 83 and +0. 23 points on NABirds and CUB-200, respectively.
1 code implementation • 23 Oct 2023 • Tin Nguyen, Jiannan Xu, Aayushi Roy, Hal Daumé III, Marine Carpuat
We apply this method in the context of content moderation of potential hate speech, and its differential impact on Asian vs. non-Asian proxy moderators, across explanation approaches (saliency map and counterfactual explanation).
no code implementations • 12 Oct 2023 • Navita Goyal, Connor Baumler, Tin Nguyen, Hal Daumé III
In this work, we study the effect of the presence of protected and proxy features on participants' perception of model fairness and their ability to improve demographic parity over an AI alone.
no code implementations • 1 Nov 2022 • Amira Alotaibi, Tarik Alafif, Faris Alkhilaiwi, Yasser Alatawi, Hassan Althobaiti, Abdulmajeed Alrefaei, Yousef M Hawsawi, Tin Nguyen
Breast cancer is the most common cancer in the world and the second most common type of cancer that causes death in women.