基本信息:
- 专利标题： SALIENCY MAPS FOR DEEP LEARNING MODELS
- 申请号：EP22212190.7 申请日：2022-12-08
- 公开(公告)号：EP4372695A1 公开(公告)日：2024-05-22
- 发明人： WEHLE, Simon , GOOßEN, Andre , LOSSAU, Tanja , GESSERT, Nils Thorben , PETERS, Jochen , WAECHTER-STEHLE, Irina , WEBER, Frank Michael , PRATER, David
- 申请人： Koninklijke Philips N.V.
- 申请人地址： NL 5656 AG Eindhoven High Tech Campus 52
- 专利权人： Koninklijke Philips N.V.
- 当前专利权人： Koninklijke Philips N.V.
- 当前专利权人地址： NL 5656 AG Eindhoven High Tech Campus 52
- 代理机构： Philips Intellectual Property & Standards
- 优先权： US 202263427048 P 2022.11.21
- 主分类号： G06V10/25
- IPC分类号： G06V10/25 ; G06V10/44 ; G06V10/46 ; G06V10/772 ; G06V10/776 ; G06V10/82 ; G06F18/2132 ; G06F18/21 ; G06F18/28 ; G06T7/00
摘要：
A method and system for providing saliency maps for a deep learning model. The method comprises inputting an input image into the deep learning model trained to output a metric score, from a plurality of metric scores, for the input image. A supportive saliency map is generated for the input image, from the deep learning model, corresponding to a first range of the metric scores for the image, thereby providing one or more supportive regions of the image indicative of the first range of metric scores. A distractive saliency map is also generated for the image, from the deep learning model, corresponding to a second range of the metric scores for the image, thereby providing one or more distractive regions of the image indicative of the second range of metric scores.