A survey of deep learning for low-shot object detection
Object detection has achieved a huge breakthrough with deep neural networks and massive
annotated data. However, current detection methods cannot be directly transferred to the …
annotated data. However, current detection methods cannot be directly transferred to the …
Few-Shot Object Detection in Remote Sensing Images via Label-Consistent Classifier and Gradual Regression
Y Liu, Z Pan, J Yang, B Zhang, G Zhou… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
With the abomination of time-consuming or even impractical large-scale labeling, few-shot
object detection (FSOD) based on natural scenes has attracted extensive attention …
object detection (FSOD) based on natural scenes has attracted extensive attention …
Transformation-invariant network for few-shot object detection in remote-sensing images
Object detection in remote-sensing images (RSIs) relies on a large amount of labeled data
for training. However, the increasing number of new categories and class imbalance make …
for training. However, the increasing number of new categories and class imbalance make …
SD-FSOD: Self-Distillation Paradigm via Distribution Calibration for Few-Shot Object Detection
Few-shot object detection (FSOD) aims to detect novel targets with only a few instances of
the associated samples. Although combinations of distillation techniques and meta-learning …
the associated samples. Although combinations of distillation techniques and meta-learning …
SNIDA: Unlocking Few-Shot Object Detection with Non-linear Semantic Decoupling Augmentation
Y Wang, X Zou, L Yan, S Zhong… - Proceedings of the …, 2024 - openaccess.thecvf.com
Once only a few-shot annotated samples are available the performance of learning-based
object detection would be heavily dropped. Many few-shot object detection (FSOD) methods …
object detection would be heavily dropped. Many few-shot object detection (FSOD) methods …
An efficient few-shot object detection method for railway intrusion via fine-tune approach and contrastive learning
T Ye, Z Zheng, X Li, Z Zhao… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Railway intrusion detection plays an important role in the railway intelligent transportation
system, assisting the safe operation of trains. The existing deep-learning-based object …
system, assisting the safe operation of trains. The existing deep-learning-based object …
Distribution-Aware and Class-Adaptive Aggregation for Few-Shot Hyperspectral Image Classification
Recently, few-shot learning based on meta-learning has shown great potential in
hyperspectral image classification (HSIC) due to its excellent adaptability to limited training …
hyperspectral image classification (HSIC) due to its excellent adaptability to limited training …
Exact Fusion via Feature Distribution Matching for Few-shot Image Generation
Y Zhou, Y Ye, P Zhang, X Wei… - Proceedings of the …, 2024 - openaccess.thecvf.com
Few-shot image generation as an important yet challenging visual task still suffers from the
trade-off between generation quality and diversity. According to the principle of feature …
trade-off between generation quality and diversity. According to the principle of feature …
Beyond Few-shot Object Detection: A Detailed Survey
V Chudasama, H Sarkar, P Wasnik… - arXiv preprint arXiv …, 2024 - arxiv.org
Object detection is a critical field in computer vision focusing on accurately identifying and
locating specific objects in images or videos. Traditional methods for object detection rely on …
locating specific objects in images or videos. Traditional methods for object detection rely on …
CRTED: Few-Shot Object Detection via Correlation-RPN and Transformer Encoder–Decoder
J Chen, K Xu, Y Ning, L Jiang, Z Xu - Electronics, 2024 - mdpi.com
Few-shot object detection (FSOD) aims to address the challenge of requiring a substantial
number of annotations for training in conventional object detection, which is very labor …
number of annotations for training in conventional object detection, which is very labor …