{"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/reduction-of-class-activation-uncertainty","title":"Reduction of Class Activation Uncertainty with Background Information","arxiv_id":"2305.03238","date":"2023-05-05","proceeding":null,"authors":["H M Dipu Kabir"],"abstract":"Multitask learning is a popular approach to training high-performing neural networks with improved generalization. In this paper, we propose a background class to achieve improved generalization at a lower computation compared to multitask learning to help researchers and organizations with limited computation power. We also present a methodology for selecting background images and discuss potential future improvements. We apply our approach to several datasets and achieve improved generalization with much lower computation. Through the class activation mappings (CAMs) of the trained models, we observed the tendency towards looking at a bigger picture with the proposed model training methodology. Applying the vision transformer with the proposed background class, we receive state-of-the-art (SOTA) performance on CIFAR-10C, Caltech-101, and CINIC-10 datasets. Example scripts are available in the `CAM' folder of the following GitHub Repository: github.com/dipuk0506/UQ","url_abs":"https://arxiv.org/abs/2305.03238v6","url_pdf":"https://arxiv.org/pdf/2305.03238v6.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":"reduction-of-class-activation-uncertainty","repo_url":"https://github.com/dipuk0506/uq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"reduction-of-class-activation-uncertainty","repo_url":"https://github.com/dipuk0506/SpinalNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"satellite-image-classification","task_name":"Satellite Image Classification"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/classification-on-cifar-10c","task":"Classification","dataset":"CIFAR-10C","model":"ViT-L/16 (Background)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy on Brightness Corrupted Images":"99.03"},"uses_additional_data":true},{"leaderboard":"/sota/fine-grained-image-classification-on-caltech","task":"Fine-Grained Image Classification","dataset":"Caltech-101","model":"VIT-L/16","rank_in_archive_order":1,"of":18,"metrics":{"Top-1 Error Rate":"1.98%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"VIT-L/16 (Spinal FC, Background)","rank_in_archive_order":19,"of":265,"metrics":{"Percentage correct":"99.05"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"VIT-L/16 (Spinal FC, Background)","rank_in_archive_order":9,"of":211,"metrics":{"Percentage correct":"93.31"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cinic-10","task":"Image Classification","dataset":"CINIC-10","model":"VIT-L/16 (Spinal FC, Background)","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"95.80"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-flowers-102","task":"Image Classification","dataset":"Flowers-102","model":"VIT-L/16 (Background)","rank_in_archive_order":2,"of":52,"metrics":{"Accuracy":"99.75"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}