{"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/luminet-the-bright-side-of-perceptual","title":"LumiNet: The Bright Side of Perceptual Knowledge Distillation","arxiv_id":"2310.03669","date":"2023-10-05","proceeding":null,"authors":["Md. Ismail Hossain","M M Lutfe Elahi","Sameera Ramasinghe","Ali Cheraghian","Fuad Rahman","Nabeel Mohammed","Shafin Rahman"],"abstract":"In knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based approaches, which aim to distill `dark knowledge' from teachers, typically exhibit inferior performance compared to feature-based methods. To bridge this gap, we present LumiNet, a novel knowledge distillation algorithm designed to enhance logit-based distillation. We introduce the concept of 'perception', aiming to calibrate logits based on the model's representation capability. This concept addresses overconfidence issues in logit-based distillation method while also introducing a novel method to distill knowledge from the teacher. It reconstructs the logits of a sample/instances by considering relationships with other samples in the batch. LumiNet excels on benchmarks like CIFAR-100, ImageNet, and MSCOCO, outperforming leading feature-based methods, e.g., compared to KD with ResNet18 and MobileNetV2 on ImageNet, it shows improvements of 1.5% and 2.05%, respectively.","url_abs":"https://arxiv.org/abs/2310.03669v2","url_pdf":"https://arxiv.org/pdf/2310.03669v2.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":"luminet-the-bright-side-of-perceptual","repo_url":"https://github.com/ismail31416/luminet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/classification-on-cifar-100","task":"Classification","dataset":"CIFAR-100","model":"ResNet8×4","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"77.50"},"uses_additional_data":false},{"leaderboard":"/sota/knowledge-distillation-on-cifar-100","task":"Knowledge Distillation","dataset":"CIFAR-100","model":"resnet8x4 (T: resnet32x4 S: resnet8x4)","rank_in_archive_order":8,"of":27,"metrics":{"Top-1 Accuracy (%)":"77.50"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}