You Only Explain Once.
CoRR(2023)
摘要
In this paper, we propose a new black-box explainability algorithm and tool,
YO-ReX, for efficient explanation of the outputs of object detectors. The new
algorithm computes explanations for all objects detected in the image
simultaneously. Hence, compared to the baseline, the new algorithm reduces the
number of queries by a factor of 10X for the case of ten detected objects. The
speedup increases further with with the number of objects. Our experimental
results demonstrate that YO-ReX can explain the outputs of YOLO with a
negligible overhead over the running time of YOLO. We also demonstrate similar
results for explaining SSD and Faster R-CNN. The speedup is achieved by
avoiding backtracking by combining aggressive pruning with a causal analysis.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要