# Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation Source: [Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:40:59.400Z Authors: Bowen Wang, Liangzhi Li, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara, Yasushi Yagi Published: 2020-10-19T13:08:15.000Z ## Abstract Semantic video segmentation is a key challenge for various applications. This paper presents a new model named Noisy-LSTM, which is trainable in an end-to-end manner, with convolutional LSTMs (ConvLSTMs) to leverage the temporal coherency in video frames. We also present a simple yet effective training strategy, which replaces a frame in video sequence with noises. This strategy spoils the temporal coherency in video frames during training and thus makes the temporal links in ConvLSTMs unreliable, which may consequently improve feature extraction from video frames, as well as serve as a regularizer to avoid overfitting, without requiring extra data annotation or computational costs. Experimental results demonstrate that the proposed model can achieve state-of-the-art performances in both the CityScapes and EndoVis2018 datasets. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()