BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks

no code implementations • 1 Apr 2024 • Zhiyuan Cheng, Zhaoyi Liu, Tengda Guo, Shiwei Feng, Dongfang Liu, Mingjie Tang, Xiangyu Zhang

Our attack prototype, named BadPart, is evaluated on both MDE and OFE tasks, utilizing a total of 7 models.

Adversarial Robustness Autonomous Driving +3

Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition

no code implementations • 23 Mar 2023 • Haoyu Tang, Zhaoyi Liu, Chang Zeng, Xinfeng Li

To overcome the drawback of universal Transformer models for the application of ASR on edge devices, we propose a solution that can reuse the block in Transformer models for the occasion of the small footprint ASR system, which meets the objective of accommodating resource limitations without compromising recognition accuracy.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Filter and evolve: progressive pseudo label refining for semi-supervised automatic speech recognition

no code implementations • 28 Oct 2022 • Zezhong Jin, Dading Zhong, Xiao Song, Zhaoyi Liu, Naipeng Ye, Qingcheng Zeng

The model is iteratively updated to correct the unreliable pseudo labels to minimize the effect of noisy labels.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2