An end-to-end deep generative approach with meta-learning optimization for zero-shot object classification
Zero-shot object classification aims to recognize the object of unseen classes whose
supervised data are unavailable in the training stage. Recent zero-shot learning (ZSL) …
supervised data are unavailable in the training stage. Recent zero-shot learning (ZSL) …
Automatic RFI identification for Sentinel-1 based on Siamese-type deep CNN using repeat-pass images
Since the start of the Sentinel-1 (S-1) mission, numerous cases of severe image degradation
caused by radio frequency interference (RFI) have been reported, which puts forward an …
caused by radio frequency interference (RFI) have been reported, which puts forward an …
ABNT: Attention Binary Navigation Tree for Fine-Grained Visual Classification
B Ding, X Xu, X Bao, N Yan… - 2024 International Joint …, 2024 - ieeexplore.ieee.org
Fine-grained visual categorization (FGVC) presents a notable challenge owing to the high
intra-class variance and minimal inter-class variability. In multi-stage FGVC tasks, the initial …
intra-class variance and minimal inter-class variability. In multi-stage FGVC tasks, the initial …
[PDF][PDF] 基于注意力机制和知识蒸馏的小样本增量学习
崔颖, 徐晓峰, 包象琳, 刘传才 - 计算机与数字工程, 2024 - jsj.journal.cssc709.net
摘要目前小样本学习模型主要关注在小样本类别上的性能, 却忽视了在辅助集上的性能.
针对此问题, 提出一种基于注意力机制和知识蒸馏的小样本增量学习模型 …
针对此问题, 提出一种基于注意力机制和知识蒸馏的小样本增量学习模型 …
ALMA: Adjustable Location and Multi-Angle Attention for Fine-Grained Visual Classification
B Ding, X Xu, X Bao, N Yan… - 2024 27th International …, 2024 - ieeexplore.ieee.org
Fine-grained visual classification (FGVC) is a challenging but realistic problem that
recognizes objects from common categories with subtle differences. Most previous work …
recognizes objects from common categories with subtle differences. Most previous work …
End-to-end supervised zero-shot learning with meta-learning strategy
Zero-shot learning (ZSL) is a challenging but practical task in the computer vision field. ZSL
tries to recognize new unknown categories by provided with training data from other known …
tries to recognize new unknown categories by provided with training data from other known …
Most Classic Problems Remain NP-Hard on Relative Neighborhood Graphs and Their Relatives
Proximity graphs have been studied for several decades, motivated by applications in
computational geometry, geography, data mining, and many other fields. However, the …
computational geometry, geography, data mining, and many other fields. However, the …
[PDF][PDF] Proximity and Intractibility
P Kunz - fpt.akt.tu-berlin.de
Proximity graphs are induced by sets of points in the plane or higher-dimensional structures.
Such graphs describe which sets of points are close to one another and which are not …
Such graphs describe which sets of points are close to one another and which are not …