Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation
Current state-of-the-art approaches for Semi-supervised Video Object Segmentation (Semi-VOS) propagates information from previous frames to generate segmentation mask for the current frame. This results in high-quality segmentation across challenging scenarios such as changes in appearance and occlusion. But it also leads to unnecessary computations for stationary or slow-moving objects where the change across frames is minimal. In this work, we exploit this observation by using temporal information to quickly identify frames with minimal change and skip the heavyweight mask generation step. To realize this efficiency, we propose a novel dynamic network that estimates change across frames and decides which path -- computing a full network or reusing previous frame's feature -- to choose depending on the expected similarity. Experimental results show that our approach significantly improves inference speed without much accuracy degradation on challenging Semi-VOS datasets -- DAVIS 16, DAVIS 17, and YouTube-VOS. Furthermore, our approach can be applied to multiple Semi-VOS methods demonstrating its generality. The code is available in https://github.com/HYOJINPARK/Reuse_VOS.
Code (1)
Tasks
One-shot visual object segmentationSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic SegmentationSimilar Papers 제목 키워드 기반
SLRNet: Semi-Supervised Semantic Segmentation Via Label Reuse for Human Decomposition Images
Semantic segmentation is a challenging computer vision task demanding a significant amount of pixel-level annotated data. Producing such data is a time-consuming and costly process, especially for domains with a scarcity…
SegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationRevisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning
Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent reasoning capabilities in large language models. However, most existing CoT methods use reasoning chains mainly as inference-tim…
Multifunctionality in embodied agents: Three levels of neural reuse
The brain in conjunction with the body is able to adapt to new environments and perform multiple behaviors through reuse of neural resources and transfer of existing behavioral traits. Although mechanisms that underlie t…
Optimal and Safe Estimation for High-Dimensional Semi-Supervised Learning
We consider the estimation problem in high-dimensional semi-supervised learning. Our goal is to investigate when and how the unlabeled data can be exploited to improve the estimation of the regression parameters of linea…
parameter estimationregressionVocal Bursts Intensity PredictionCalibrating Uncertainty for Semi-Supervised Crowd Counting
Semi-supervised crowd counting is an important yet challenging task. A popular approach is to iteratively generate pseudo-labels for unlabeled data and add them to the training set. The key is to use uncertainty to selec…
Crowd Counting