{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/influence-of-image-classification-accuracy-on","title":"Influence of Image Classification Accuracy on Saliency Map Estimation","arxiv_id":"1807.10657","date":"2018-07-27","proceeding":null,"authors":["Taiki Oyama","Takao Yamanaka"],"abstract":"Saliency map estimation in computer vision aims to estimate the locations\nwhere people gaze in images. Since people tend to look at objects in images,\nthe parameters of the model pretrained on ImageNet for image classification are\nuseful for the saliency map estimation. However, there is no research on the\nrelationship between the image classification accuracy and the performance of\nthe saliency map estimation. In this paper, it is shown that there is a strong\ncorrelation between image classification accuracy and saliency map estimation\naccuracy. We also investigated the effective architecture based on multi scale\nimages and the upsampling layers to refine the saliency-map resolution. Our\nmodel achieved the state-of-the-art accuracy on the PASCAL-S, OSIE, and MIT1003\ndatasets. In the MIT Saliency Benchmark, our model achieved the best\nperformance in some metrics and competitive results in the other metrics.","url_abs":"http://arxiv.org/abs/1807.10657v1","url_pdf":"http://arxiv.org/pdf/1807.10657v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"influence-of-image-classification-accuracy-on","repo_url":"https://github.com/islab-sophia/odisal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}