From the source
From the source
LG AI Research introduces SISE (Semantic Input Sampling for Explanation), a novel visual explainable AI method that improves faithfulness and reduces computation time compared to existing
XAI methods.
The method is described in their AAAI-21 paper.
From the source
LG AI Research has developed a novel XAI algorithm, called "Semantic Input Sampling for Explanation (SISE)" in collaboration with Prof. Konstantinos Plataniotis at the University of Toronto. It achieves higher faithfulness and correctness than the previously mentioned XAI methods. Additionally, it takes less computation time.
lgresearch.ai
