Yi Yang, Yueyuan Zheng, Didan Deng, Jindi Zhang, Yongxiang Huang, Yumeng Yang, J. Hsiao, Caleb Chen Cao
{"title":"HSI:人类显著性模仿者的基准显著性为基础的模型解释","authors":"Yi Yang, Yueyuan Zheng, Didan Deng, Jindi Zhang, Yongxiang Huang, Yumeng Yang, J. Hsiao, Caleb Chen Cao","doi":"10.1609/hcomp.v10i1.22002","DOIUrl":null,"url":null,"abstract":"Model explanations are generated by XAI (explainable AI) methods to help people understand and interpret machine learning models. To study XAI methods from the human perspective, we propose a human-based benchmark dataset, i.e., human saliency benchmark (HSB), for evaluating saliency-based XAI methods. Different from existing human saliency annotations where class-related features are manually and subjectively labeled, this benchmark collects more objective human attention on vision information with a precise eye-tracking device and a novel crowdsourcing experiment. Taking the labor cost of human experiment into consideration, we further explore the potential of utilizing a prediction model trained on HSB to mimic saliency annotating by humans. Hence, a dense prediction problem is formulated, and we propose an encoder-decoder architecture which combines multi-modal and multi-scale features to produce the human saliency maps. Accordingly, a pretraining-finetuning method is designed to address the model training problem. Finally, we arrive at a model trained on HSB named human saliency imitator (HSI). We show, through an extensive evaluation, that HSI can successfully predict human saliency on our HSB dataset, and the HSI-generated human saliency dataset on ImageNet showcases the ability of benchmarking XAI methods both qualitatively and quantitatively.","PeriodicalId":87339,"journal":{"name":"Proceedings of the ... AAAI Conference on Human Computation and Crowdsourcing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"HSI: Human Saliency Imitator for Benchmarking Saliency-Based Model Explanations\",\"authors\":\"Yi Yang, Yueyuan Zheng, Didan Deng, Jindi Zhang, Yongxiang Huang, Yumeng Yang, J. Hsiao, Caleb Chen Cao\",\"doi\":\"10.1609/hcomp.v10i1.22002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Model explanations are generated by XAI (explainable AI) methods to help people understand and interpret machine learning models. To study XAI methods from the human perspective, we propose a human-based benchmark dataset, i.e., human saliency benchmark (HSB), for evaluating saliency-based XAI methods. Different from existing human saliency annotations where class-related features are manually and subjectively labeled, this benchmark collects more objective human attention on vision information with a precise eye-tracking device and a novel crowdsourcing experiment. Taking the labor cost of human experiment into consideration, we further explore the potential of utilizing a prediction model trained on HSB to mimic saliency annotating by humans. Hence, a dense prediction problem is formulated, and we propose an encoder-decoder architecture which combines multi-modal and multi-scale features to produce the human saliency maps. Accordingly, a pretraining-finetuning method is designed to address the model training problem. Finally, we arrive at a model trained on HSB named human saliency imitator (HSI). We show, through an extensive evaluation, that HSI can successfully predict human saliency on our HSB dataset, and the HSI-generated human saliency dataset on ImageNet showcases the ability of benchmarking XAI methods both qualitatively and quantitatively.\",\"PeriodicalId\":87339,\"journal\":{\"name\":\"Proceedings of the ... AAAI Conference on Human Computation and Crowdsourcing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-10-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the ... AAAI Conference on Human Computation and Crowdsourcing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1609/hcomp.v10i1.22002\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ... AAAI Conference on Human Computation and Crowdsourcing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1609/hcomp.v10i1.22002","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
HSI: Human Saliency Imitator for Benchmarking Saliency-Based Model Explanations
Model explanations are generated by XAI (explainable AI) methods to help people understand and interpret machine learning models. To study XAI methods from the human perspective, we propose a human-based benchmark dataset, i.e., human saliency benchmark (HSB), for evaluating saliency-based XAI methods. Different from existing human saliency annotations where class-related features are manually and subjectively labeled, this benchmark collects more objective human attention on vision information with a precise eye-tracking device and a novel crowdsourcing experiment. Taking the labor cost of human experiment into consideration, we further explore the potential of utilizing a prediction model trained on HSB to mimic saliency annotating by humans. Hence, a dense prediction problem is formulated, and we propose an encoder-decoder architecture which combines multi-modal and multi-scale features to produce the human saliency maps. Accordingly, a pretraining-finetuning method is designed to address the model training problem. Finally, we arrive at a model trained on HSB named human saliency imitator (HSI). We show, through an extensive evaluation, that HSI can successfully predict human saliency on our HSB dataset, and the HSI-generated human saliency dataset on ImageNet showcases the ability of benchmarking XAI methods both qualitatively and quantitatively.