Review of Zero-Shot Remote Sensing Image Scene Classification
IEEE Journal of Selected Topics in Applied Earth Observations and Remote SensingIn recent years, remote sensing (RS) image scene classification methods have experienced notable development due to the powerful feature extraction ability of deep learning. However, current methods for RS image scene classification (RSSC) tasks struggle
Xiaomeng Tan +6 more
doaj +3 more sources
Zero-Shot Audio Classification using Image Embeddings [PDF]
2022 30th European Signal Processing Conference (EUSIPCO), 2022 Accepted to the European Signal Processing Conference (EUSIPCO ...
Xie Huang +3 more
openaire +5 more sources
Gaze Embeddings for Zero-Shot Image Classification [PDF]
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 Zero-shot image classification using auxiliary information, such as attributes describing discriminative object properties, requires time-consuming annotation by domain experts. We instead propose a method that relies on human gaze as auxiliary information, exploiting that even non-expert users have a natural ability to judge class membership.
Nour Karessli +3 more
openaire +9 more sources
Image-free Classifier Injection for Zero-Shot Classification [PDF]
2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023 Accepted at ICCV ...
Christensen, Anders +4 more
core +8 more sources
Generative Adversarial Networks for Zero-Shot Remote Sensing Scene Classification
Applied Sciences, 2022 Deep learning-based methods succeed in remote sensing scene classification (RSSC). However, current methods require training on a large dataset, and if a class does not appear in the training set, it does not work well.
Zihao Li +4 more
doaj +2 more sources
Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders [PDF]
Scientific ReportsDeep neural networks are increasingly used in medical imaging for tasks such as pathological classification, but they face challenges due to the scarcity of high-quality, expert-labeled training data.
Jongseong Jang +5 more
doaj +2 more sources
Zero-shot incremental learning using spatial-frequency feature representations [PDF]
Scientific ReportsZero-shot incremental learning aims to enable a model to generalize to new classes without forgetting previously learned classes. However, the semantic gap between old and new sample classes can lead to catastrophic forgetting.
Jie Ren +3 more
doaj +2 more sources
Text2Model: Text-based Model Induction for Zero-shot Image Classification [PDF]
Findings of the Association for Computational Linguistics: EMNLP 2024We address the challenge of building task-agnostic classifiers using only text descriptions, demonstrating a unified approach to image classification, 3D point cloud classification, and action recognition from scenes. Unlike approaches that learn a fixed representation of the output classes, we generate at inference time a model tailored to a query ...
Ohad Amosy +5 more
openaire +3 more sources
Prognostication of Unseen Objects using Zero-Shot Learning with a Complete Case Analysis [PDF]
Interdisciplinary Description of Complex Systems, 2022 Generally, for a machine learning model to perform well, the data instances on which the model is being trained have to be relevant to the use case.
Srinivasa L. Chakravarthy +1 more
doaj +1 more source
Zero-Shot Image Classification Based on Improved Variational Auto-encoder
Taiyuan Ligong Daxue xuebao, 2021 In the process of zero-shot image classification, problems such as high acquisition cost for samples of known categories and domain drift were addressed.
Zhen CAO, Hongwei XIE
doaj +1 more source