TY - JOUR AU - Zołna, Konrad AU - Geras, Krzysztof J. AU - Cho, Kyunghyun PY - 2019/07/17 Y2 - 2024/03/28 TI - Classifier-Agnostic Saliency Map Extraction JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 33 IS - 01 SE - Student Abstract Track DO - 10.1609/aaai.v33i01.330110087 UR - https://ojs.aaai.org/index.php/AAAI/article/view/5180 SP - 10087-10088 AB - <p>Extracting saliency maps, which indicate parts of the image important to classification, requires many tricks to achieve satisfactory performance when using classifier-dependent methods. Instead, we propose classifier-agnostic saliency map extraction. This allows to find all parts of the image that any classifier could use, not just one given in advance. This way we extract much higher quality saliency maps.</p> ER -