{"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/ilgnet-inception-modules-with-connected-local","title":"ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain Adaptation","arxiv_id":"1610.02256","date":"2016-10-07","proceeding":null,"authors":["Xin Jin","Le Wu","Xiao-Dong Li","Xiaokun Zhang","Jingying Chi","Siwei Peng","Shiming Ge","Geng Zhao","Shuying Li"],"abstract":"In this paper, we address a challenging problem of aesthetic image\nclassification, which is to label an input image as high or low aesthetic\nquality. We take both the local and global features of images into\nconsideration. A novel deep convolutional neural network named ILGNet is\nproposed, which combines both the Inception modules and an connected layer of\nboth Local and Global features. The ILGnet is based on GoogLeNet. Thus, it is\neasy to use a pre-trained GoogLeNet for large-scale image classification\nproblem and fine tune our connected layers on an large scale database of\naesthetic related images: AVA, i.e. \\emph{domain adaptation}. The experiments\nreveal that our model achieves the state of the arts in AVA database. Both the\ntraining and testing speeds of our model are higher than those of the original\nGoogLeNet.","url_abs":"http://arxiv.org/abs/1610.02256v3","url_pdf":"http://arxiv.org/pdf/1610.02256v3.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":"ilgnet-inception-modules-with-connected-local","repo_url":"https://github.com/BestiVictory/ILGnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":null},{"paper_slug":"ilgnet-inception-modules-with-connected-local","repo_url":"https://github.com/Kin-Lau/ILGnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"aesthetics-quality-assessment","task_name":"Aesthetics Quality Assessment"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"googlenet","method_name":"GoogLeNet"},{"method_slug":"inception-module","method_name":"Inception Module"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}