ﻻ يوجد ملخص باللغة العربية
While fully-supervised deep learning yields good models for urban scene semantic segmentation, these models struggle to generalize to new environments with different lighting or weather conditions for instance. In addition, producing the extensive pixel-level annotations that the task requires comes at a great cost. Unsupervised domain adaptation (UDA) is one approach that tries to address these issues in order to make such systems more scalable. In particular, self-supervised learning (SSL) has recently become an effective strategy for UDA in semantic segmentation. At the core of such methods lies `pseudo-labeling, that is, the practice of assigning high-confident class predictions as pseudo-labels, subsequently used as true labels, for target data. To collect pseudo-labels, previous works often rely on the highest softmax score, which we here argue as an unfavorable confidence measurement. In this work, we propose Entropy-guided Self-supervised Learning (ESL), leveraging entropy as the confidence indicator for producing more accurate pseudo-labels. On different UDA benchmarks, ESL consistently outperforms strong SSL baselines and achieves state-of-the-art results.
Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by varying illumin
Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints. We focus on source-free domain adaptation for semantic se
Contrastive learning has shown superior performance in embedding global and spatial invariant features in computer vision (e.g., image classification). However, its overall success of embedding local and spatial variant features is still limited, esp
Unsupervised domain adaptation (UDA) becomes more and more popular in tackling real-world problems without ground truth of the target domain. Though a mass of tedious annotation work is not needed, UDA unavoidably faces the problem how to narrow the
Convolutional neural network-based approaches have achieved remarkable progress in semantic segmentation. However, these approaches heavily rely on annotated data which are labor intensive. To cope with this limitation, automatically annotated data g