{"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/revisiting-pre-training-in-audio-visual","title":"Revisiting Pre-training in Audio-Visual Learning","arxiv_id":"2302.03533","date":"2023-02-07","proceeding":null,"authors":["Ruoxuan Feng","Wenke Xia","Di Hu"],"abstract":"Pre-training technique has gained tremendous success in enhancing model performance on various tasks, but found to perform worse than training from scratch in some uni-modal situations. This inspires us to think: are the pre-trained models always effective in the more complex multi-modal scenario, especially for the heterogeneous modalities such as audio and visual ones? We find that the answer is No. Specifically, we explore the effects of pre-trained models on two audio-visual learning scenarios: cross-modal initialization and multi-modal joint learning. When cross-modal initialization is applied, the phenomena of \"dead channel\" caused by abnormal Batchnorm parameters hinders the utilization of model capacity. Thus, we propose Adaptive Batchnorm Re-initialization (ABRi) to better exploit the capacity of pre-trained models for target tasks. In multi-modal joint learning, we find a strong pre-trained uni-modal encoder would bring negative effects on the encoder of another modality. To alleviate such problem, we introduce a two-stage Fusion Tuning strategy, taking better advantage of the pre-trained knowledge while making the uni-modal encoders cooperate with an adaptive masking method. The experiment results show that our methods could further exploit pre-trained models' potential and boost performance in audio-visual learning.","url_abs":"https://arxiv.org/abs/2302.03533v2","url_pdf":"https://arxiv.org/pdf/2302.03533v2.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":"revisiting-pre-training-in-audio-visual","repo_url":"https://github.com/gewu-lab/revisiting-pre-training-in-audio-visual-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-visual-learning","task_name":"audio-visual learning"}],"methods":[{"method_slug":"adaptive-masking","method_name":"Adaptive Masking"},{"method_slug":"l1-regularization","method_name":"L1 Regularization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}