Semmae: Semantic-guided masking for learning masked autoencoders

G Li, H Zheng, D Liu, C Wang, B Su… - Advances in Neural …, 2022‏ - proceedings.neurips.cc
Recently, significant progress has been made in masked image modeling to catch up to
masked language modeling. However, unlike words in NLP, the lack of semantic …

Leaving reality to imagination: Robust classification via generated datasets

H Bansal, A Grover - arxiv preprint arxiv:2302.02503, 2023‏ - arxiv.org
Recent research on robustness has revealed significant performance gaps between neural
image classifiers trained on datasets that are similar to the test set, and those that are from a …

Mask-guided correlation learning for few-shot segmentation in remote sensing imagery

S Li, F Liu, L Jiao, X Liu, P Chen… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Few-shot segmentation aims to segment specific objects in a query image based on a few
densely annotated images and has been extensively studied in recent years. In remote …

Adapt before comparison: A new perspective on cross-domain few-shot segmentation

J Herzog - Proceedings of the IEEE/CVF conference on …, 2024‏ - openaccess.thecvf.com
Few-shot segmentation performance declines substantially when facing images from a
domain different than the training domain effectively limiting real-world use cases. To …

Latency-free driving scene prediction for on-road teledriving with future-image-generation

KW Lee, DK Ko, YJ Kim, JH Ryu… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Teledriving could serve as a practical solution for handling unforeseen situations in
autonomous driving. However, the latency of transmission networks remains a prominent …

Adversarial example detection using semantic graph matching

Y Gong, S Wang, X Jiang, L Yin, F Sun - Applied Soft Computing, 2023‏ - Elsevier
Deep neural networks have recently been found to be vulnerable to adversarial examples,
which can deceive attacked models with high confidence. This has given rise to significant …

Improving few-shot part segmentation using coarse supervision

O Saha, Z Cheng, S Maji - European Conference on Computer Vision, 2022‏ - Springer
A significant bottleneck in training deep networks for part segmentation is the cost of
obtaining detailed annotations. We propose a framework to exploit coarse labels such as …

ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning

Z Ye, SN Gowda, S Chen, X Huang, H Xu… - The Thirteenth …, 2025‏ - openreview.net
Zero-shot Learning (ZSL) aims to enable classifiers to identify unseen classes. This is
typically achieved by generating visual features for unseen classes based on learned visual …

PartSeg: Few-shot part segmentation via part-aware prompt learning

M Han, H Zheng, C Wang, Y Luo, H Hu, J Zhang… - Pattern Recognition, 2025‏ - Elsevier
In this work, we address the task of few-shot part segmentation, which aims to segment the
different parts of an unseen object using very few labeled examples. It has been found that …

Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges

N Catalano, M Matteucci - arxiv preprint arxiv:2304.05832, 2023‏ - arxiv.org
Semantic segmentation, vital for applications ranging from autonomous driving to robotics,
faces significant challenges in domains where collecting large annotated datasets is difficult …