40 citations · 63 across the 4 of their papers we have counts for
4 papers
Rethinking Attention-Model Explainability through Faithfulness Violation Test
Yibing Liu, Haoliang Li, Yangyang Guo +3
Attention mechanisms are dominating the explainability of deep models. They produce probability distributions over the input, which are widely deemed as feature-importance indicato…
No-Reference Image Quality Assessment by Hallucinating Pristine Features
Baoliang Chen, Lingyu Zhu, Chenqi Kong +3
In this paper, we propose a no-reference (NR) image quality assessment (IQA) method via feature level pseudo-reference (PR) hallucination. The proposed quality assessment framework…
Detect and Locate: Exposing Face Manipulation by Semantic- and Noise-level Telltales
Chenqi Kong, Baoliang Chen, Haoliang Li +3
The technological advancements of deep learning have enabled sophisticated face manipulation schemes, raising severe trust issues and security concerns in modern society. Generally…
Faster super-resolution imaging with auto-correlation two-step deconvolution
Weisong Zhao, Jian Liu, Chenqi Kong +7
Despite super-resolution fluorescence blinking microscopes break the diffraction limit, the intense phototoxic illumination and long-term image sequences thus far still pose to maj…