6 papers
Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scaling
Ting-An Chen, Chin-Yuan Yeh, De-Nian Yang
Quantizing deep neural networks is essential for efficient inference on resource-constrained devices. However, most existing methods are designed for single-domain and class-balanc…
Self-guided Knowledgeable Network of Thoughts: Amplifying Reasoning with Large Language Models
Chao-Chi Chen, Chin-Yuan Yeh, Hsi-Wen Chen +2
We introduce Knowledgeable Network of Thoughts (kNoT): a prompt scheme that advances the capabilities of large language models (LLMs) beyond existing paradigms like Chain-of-Though…
Evaluating Adversarial Robustness in the Spatial Frequency Domain
Keng-Hsin Liao, Chin-Yuan Yeh, Hsi-Wen Chen +1
Convolutional Neural Networks (CNNs) have dominated the majority of computer vision tasks. However, CNNs' vulnerability to adversarial attacks has raised concerns about deploying t…
In Anticipation of Perfect Deepfake: Identity-anchored Artifact-agnostic Detection under Rebalanced Deepfake Detection Protocol
Wei-Han Wang, Chin-Yuan Yeh, Hsi-Wen Chen +2
As deep generative models advance, we anticipate deepfakes achieving "perfection"-generating no discernible artifacts or noise. However, current deepfake detectors, intentionally o…
SASMU: boost the performance of generalized recognition model using synthetic face dataset
Chia-Chun Chung, Pei-Chun Chang, Yong-Sheng Chen +2
Nowadays, deploying a robust face recognition product becomes easy with the development of face recognition techniques for decades. Not only profile image verification but also the…
Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial Attack
Chin-Yuan Yeh, Hsi-Wen Chen, Hong-Han Shuai +2
With the successful creation of high-quality image-to-image (Img2Img) translation GANs comes the non-ethical applications of DeepFake and DeepNude. Such misuses of img2img techniqu…