A survey on deep learning-based architectures for semantic segmentation on 2d images

I Ulku, E Akagündüz - Applied Artificial Intelligence, 2022 - Taylor & Francis
Semantic segmentation is the pixel-wise labeling of an image. Boosted by the extraordinary
ability of convolutional neural networks (CNN) in creating semantic, high-level and …

Semantic image segmentation: Two decades of research

G Csurka, R Volpi, B Chidlovskii - Foundations and Trends® …, 2022 - nowpublishers.com
Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer
vision applications, providing key information for the global understanding of an image. This …

Ecotta: Memory-efficient continual test-time adaptation via self-distilled regularization

J Song, J Lee, IS Kweon, S Choi - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
This paper presents a simple yet effective approach that improves continual test-time
adaptation (TTA) in a memory-efficient manner. TTA may primarily be conducted on edge …

Towards fewer annotations: Active learning via region impurity and prediction uncertainty for domain adaptive semantic segmentation

B Xie, L Yuan, S Li, CH Liu… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively
generates pseudo labels on unlabeled target data and retrains the network. However …

Daso: Distribution-aware semantics-oriented pseudo-label for imbalanced semi-supervised learning

Y Oh, DJ Kim, IS Kweon - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
The capability of the traditional semi-supervised learning (SSL) methods is far from real-
world application due to severely biased pseudo-labels caused by (1) class imbalance and …

Skyeye: Self-supervised bird's-eye-view semantic mapping using monocular frontal view images

N Gosala, K Petek, PLJ Drews-Jr… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Bird's-Eye-View (BEV) semantic maps have become an essential component of
automated driving pipelines due to the rich representation they provide for decision-making …

Annotator: A generic active learning baseline for lidar semantic segmentation

B Xie, S Li, Q Guo, C Liu… - Advances in Neural …, 2023 - proceedings.neurips.cc
Active learning, a label-efficient paradigm, empowers models to interactively query an oracle
for labeling new data. In the realm of LiDAR semantic segmentation, the challenges stem …

Unsupervised domain adaptation for semantic image segmentation: a comprehensive survey

G Csurka, R Volpi, B Chidlovskii - arXiv preprint arXiv:2112.03241, 2021 - arxiv.org
Semantic segmentation plays a fundamental role in a broad variety of computer vision
applications, providing key information for the global understanding of an image. Yet, the …

Mcdal: Maximum classifier discrepancy for active learning

JW Cho, DJ Kim, Y Jung… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Recent state-of-the-art active learning methods have mostly leveraged generative
adversarial networks (GANs) for sample acquisition; however, GAN is usually known to …

Signing outside the studio: Benchmarking background robustness for continuous sign language recognition

Y Jang, Y Oh, JW Cho, DJ Kim, JS Chung… - arXiv preprint arXiv …, 2022 - arxiv.org
The goal of this work is background-robust continuous sign language recognition. Most
existing Continuous Sign Language Recognition (CSLR) benchmarks have fixed …