Self Semi Supervised Neural Architecture Search for Semantic Segmentation
In this paper, we propose a Neural Architecture Search strategy based on self supervision and semi-supervised learning for the task of semantic segmentation. Our approach builds an optimized neural network (NN) model for this task by jointly solving a jigsaw pretext task discovered with self-supervised learning over unlabeled training data, and, exploiting the structure of the unlabeled data with semi-supervised learning. The search of the architecture of the NN model is performed by dynamic routing using a gradient descent algorithm. Experiments on the Cityscapes and PASCAL VOC 2012 datasets demonstrate that the discovered neural network is more efficient than a state-of-the-art hand-crafted NN model with four times less floating operations.
Code (0)
등록된 구현이 없습니다.
Tasks
Neural Architecture SearchSelf-Supervised LearningSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data
User sessions empower many search and recommendation tasks on a daily basis. Such session data are semi-structured, which encode heterogeneous relations between queries and products, and each item is described by the uns…
Entity LinkingSelf-Supervised LearningSession SearchCERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data
User sessions empower many search and recommendation tasks on a daily basis. Such session data are semi-structured, which encode heterogeneous relations between queries and products, and each item is described by the uns…
Entity LinkingSelf-Supervised LearningSession SearchSaliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation
Weakly supervised semantic segmentation (WSSS) using only image-level labels can greatly reduce the annotation cost and therefore has attracted considerable research interest. However, its performance is still inferior t…
SegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationWeakly supervised Semantic Segmentation+1Colour augmentation for improved semi-supervised semantic segmentation
Consistency regularization describes a class of approaches that have yielded state-of-the-art results for semi-supervised classification. While semi-supervised semantic segmentation proved to be more challenging, a numbe…
ClassificationSegmentationSelf-Supervised LearningSemantic Segmentation+1A Large-scale Evaluation of Pretraining Paradigms for the Detection of Defects in Electroluminescence Solar Cell Images
Pretraining has been shown to improve performance in many domains, including semantic segmentation, especially in domains with limited labelled data. In this work, we perform a large-scale evaluation and benchmarking of …
BenchmarkingDefect DetectionSegmentationSemantic Segmentation