Learning bottleneck concepts in image classification
Interpreting and explaining the behavior of deep neural networks is critical for many tasks.
Explainable AI provides a way to address this challenge, mostly by providing per-pixel …
Explainable AI provides a way to address this challenge, mostly by providing per-pixel …
Few-shot learning with dynamic graph structure preserving
In recent years, few-shot learning has received increasing attention in the Internet of Things
areas. Few-shot learning aims to distinguish unseen classes with a few labeled samples …
areas. Few-shot learning aims to distinguish unseen classes with a few labeled samples …
Textual enhanced adaptive meta-fusion for few-shot visual recognition
Few-shot learning (FSL) is a challenging task that aims to train a classifier to recognize
novel categories, where only a few annotated examples are available in each category …
novel categories, where only a few annotated examples are available in each category …
Not all instances contribute equally: Instance-adaptive class representation learning for few-shot visual recognition
Few-shot visual recognition refers to recognize novel visual concepts from a few labeled
instances. Many few-shot visual recognition methods adopt the metric-based meta-learning …
instances. Many few-shot visual recognition methods adopt the metric-based meta-learning …
Cross-domain self-taught network for few-shot hyperspectral image classification
In recent years, deep learning models, which possess powerful feature extraction abilities,
have achieved remarkable success in the classification of hyperspectral images (HSIs) …
have achieved remarkable success in the classification of hyperspectral images (HSIs) …
MetaDT: Meta decision tree with class hierarchy for interpretable few-shot learning
Few-Shot Learning (FSL) is a challenging task, which aims to recognize novel classes with
few examples. Recently, lots of methods have been proposed from the perspective of meta …
few examples. Recently, lots of methods have been proposed from the perspective of meta …
Match them up: visually explainable few-shot image classification
Few-shot learning (FSL) approaches, mostly neural network-based, assume that pre-trained
knowledge can be obtained from base (seen) classes and transferred to novel (unseen) …
knowledge can be obtained from base (seen) classes and transferred to novel (unseen) …
Meta-learning in healthcare: A survey
As a subset of machine learning, meta-learning, or learning to learn, aims at improving the
model's capabilities by employing prior knowledge and experience. A meta-learning …
model's capabilities by employing prior knowledge and experience. A meta-learning …
Dual-view data hallucination with semantic relation guidance for few-shot image recognition
H Wu, G Ye, Z Zhou, L Tian, Q Wang, L Lin - arXiv preprint arXiv …, 2024 - arxiv.org
Learning to recognize novel concepts from just a few image samples is very challenging as
the learned model is easily overfitted on the few data and results in poor generalizability …
the learned model is easily overfitted on the few data and results in poor generalizability …
Vision transformer with enhanced self-attention for few-shot ship target recognition in complex environments
Y Tian, H Meng, F Yuan, Y Ling… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Ship target recognition is essential for maritime transportation, commercial trade, maritime
security, and monitoring illegal activity. The majority of previous ship target recognition …
security, and monitoring illegal activity. The majority of previous ship target recognition …