{"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/tie-kd-teacher-independent-and-explainable","title":"TIE-KD: Teacher-Independent and Explainable Knowledge Distillation for Monocular Depth Estimation","arxiv_id":"2402.14340","date":"2024-02-22","proceeding":null,"authors":["Sangwon Choi","Daejune Choi","Duksu Kim"],"abstract":"Monocular depth estimation (MDE) is essential for numerous applications yet is impeded by the substantial computational demands of accurate deep learning models. To mitigate this, we introduce a novel Teacher-Independent Explainable Knowledge Distillation (TIE-KD) framework that streamlines the knowledge transfer from complex teacher models to compact student networks, eliminating the need for architectural similarity. The cornerstone of TIE-KD is the Depth Probability Map (DPM), an explainable feature map that interprets the teacher's output, enabling feature-based knowledge distillation solely from the teacher's response. This approach allows for efficient student learning, leveraging the strengths of feature-based distillation. Extensive evaluation of the KITTI dataset indicates that TIE-KD not only outperforms conventional response-based KD methods but also demonstrates consistent efficacy across diverse teacher and student architectures. The robustness and adaptability of TIE-KD underscore its potential for applications requiring efficient and interpretable models, affirming its practicality for real-world deployment.","url_abs":"https://arxiv.org/abs/2402.14340v1","url_pdf":"https://arxiv.org/pdf/2402.14340v1.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":"tie-kd-teacher-independent-and-explainable","repo_url":"https://github.com/hpc-lab-koreatech/tie-kd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/knowledge-distillation-on-kitti","task":"Knowledge Distillation","dataset":"KITTI","model":"TIE-KD (T: Adabins S: MobileNetV2)","rank_in_archive_order":1,"of":1,"metrics":{"RMSE":"2.4315","model size":"17.6M"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}