Domain adaptation: challenges, methods, datasets, and applications

P Singhal, R Walambe, S Ramanna, K Kotecha - IEEE access, 2023‏ - ieeexplore.ieee.org
Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well
on another set of data (target domain), which is different but has similar properties as the …

Deep-learning-based approaches for semantic segmentation of natural scene images: A review

B Emek Soylu, MS Guzel, GE Bostanci, F Ekinci… - Electronics, 2023‏ - mdpi.com
The task of semantic segmentation holds a fundamental position in the field of computer
vision. Assigning a semantic label to each pixel in an image is a challenging task. In recent …

MIC: Masked image consistency for context-enhanced domain adaptation

L Hoyer, D Dai, H Wang… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
In unsupervised domain adaptation (UDA), a model trained on source data (eg synthetic) is
adapted to target data (eg real-world) without access to target annotation. Most previous …

Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation

L Hoyer, D Dai, L Van Gool - Proceedings of the IEEE/CVF …, 2022‏ - openaccess.thecvf.com
As acquiring pixel-wise annotations of real-world images for semantic segmentation is a
costly process, a model can instead be trained with more accessible synthetic data and …

Hrda: Context-aware high-resolution domain-adaptive semantic segmentation

L Hoyer, D Dai, L Van Gool - European conference on computer vision, 2022‏ - Springer
Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source
domain (eg synthetic data) to the target domain (eg real-world data) without requiring further …

Align your prompts: Test-time prompting with distribution alignment for zero-shot generalization

J Abdul Samadh, MH Gani, N Hussein… - Advances in …, 2023‏ - proceedings.neurips.cc
The promising zero-shot generalization of vision-language models such as CLIP has led to
their adoption using prompt learning for numerous downstream tasks. Previous works have …

Ambiguity-selective consistency regularization for mean-teacher semi-supervised medical image segmentation

Z Xu, Y Wang, D Lu, X Luo, J Yan, Y Zheng… - Medical Image …, 2023‏ - Elsevier
Semi-supervised learning has greatly advanced medical image segmentation since it
effectively alleviates the need of acquiring abundant annotations from experts, wherein the …

Sepico: Semantic-guided pixel contrast for domain adaptive semantic segmentation

B **e, S Li, M Li, CH Liu, G Huang… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on
an unlabeled target domain by utilizing the supervised model trained on a labeled source …

Semi-supervised semantic segmentation with pixel-level contrastive learning from a class-wise memory bank

I Alonso, A Sabater, D Ferstl… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
This work presents a novel approach for semi-supervised semantic segmentation. The key
element of this approach is our contrastive learning module that enforces the segmentation …

V3det: Vast vocabulary visual detection dataset

J Wang, P Zhang, T Chu, Y Cao… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Recent advances in detecting arbitrary objects in the real world are trained and evaluated
on object detection datasets with a relatively restricted vocabulary. To facilitate the …