On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis

arXiv:2203.07976v3 Announce Type: replace
Abstract: Batch Normalization's (BN) unique property of depending on other samples in a batch is known to cause problems in several tasks, including sequential modeling. Yet, BN-related issues are hardly studied for long video understanding, despite the ubiquitous use of BN in CNNs (Convolutional Neural Networks) for feature extraction. Especially in surgical workflow analysis, where the lack of pretrained feature extractors has led to complex, multi-stage training pipelines, limited awareness of BN issues may have hidden …

analysis arxiv cs.cv normalization study type video workflow