Towards improving classification power for one-shot object detection

Yang, Hanqing; Lin, Yongliang; Zhang, Hong; Xu, Bin

doi:10.1016/j.neucom.2021.04.116

Cited by 13 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OSOD, as an extreme case of FSOD, involves the localization and classification for novel objects with only one sample. Recent researches [30], [60] suggest that the box regressor is capable of accurately localizing novel instances. Owing to the seriously unbalanced datasets between base and novel classes, the main source of generalization degradation is misclassifying the instances of base classes as objects of interest.…”

Section: Few-shot Object Detectionmentioning

confidence: 99%

Adaptive context- and scale-aware aggregation with feature alignment for one-shot object detection

et al. 2022

View full text Add to dashboard Cite

Section: Few-shot Object Detectionmentioning

confidence: 99%

Adaptive context- and scale-aware aggregation with feature alignment for one-shot object detection

et al. 2022

View full text Add to dashboard Cite

“…The backward mapping algorithm generates the output image for each pixel without interval. The pixel gray value of each target image is determined by the color values of the pixels of four source images after interpolation algorithm, and then the output image is generated [23][24][25].…”

Section: Build a Real-time Panorama Of Sports Dance Competitionmentioning

confidence: 99%

Real-Time Monitoring of College Sports Dance Competition Scenes Using Deep Learning Algorithms

Yang

Shan

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In order to improve the real-time detection effect, therefore, a research on real-time scene detection of sports dance competition based on deep learning is proposed. The collected scene image is grayed by using the weighted average method, and the best image interpolation is calculated by using the deep learning method, so as to realize the smooth processing of sawtooth and mosaic information generated by panoramic mapping. After selecting the cube model, the processed scene information is projected to the visual plane to construct the panorama of the competition scene. Finally, combined with the three-frame difference, the changes between adjacent image frames are calculated to obtain the moving target. The test results show that the motion detection accuracy of professional dancers can reach more than 75.0% and that of amateur dancer can reach more than 64.2%.

show abstract

“…FOC OSOD [85] also uses convolution blocks to extend the integral feature aggregation method in SiamMask:…”

Section: One-shot Object Detectionmentioning

confidence: 99%

A Survey of Deep Learning for Low-Shot Object Detection

Huang¹,

Zhang²,

Xue³

et al. 2021

Preprint

View full text Add to dashboard Cite

Object detection is a fundamental task in computer vision and image processing. Current deep learning based object detectors have been highly successful with abundant labeled data. But in real life, it is not guaranteed that each object category has enough labeled samples for training. These large object detectors are easy to overfit when the training data is limited. Therefore, it is necessary to introduce few-shot learning and zeroshot learning into object detection, which can be named low-shot object detection together. Low-Shot Object Detection (LSOD) aims to detect objects from a few or even zero labeled data, which can be categorized into few-shot object detection (FSOD) and zero-shot object detection (ZSD), respectively. This paper conducts a comprehensive survey for deep learning based FSOD and ZSD. First, this survey classifies methods for FSOD and ZSD into different categories and discusses the pros and cons of them. Second, this survey reviews dataset settings and evaluation metrics for FSOD and ZSD, then analyzes the performance of different methods on these benchmarks. Finally, this survey discusses future challenges and promising directions for FSOD and ZSD.

show abstract

Towards improving classification power for one-shot object detection

Cited by 13 publications

References 11 publications

Adaptive context- and scale-aware aggregation with feature alignment for one-shot object detection

Adaptive context- and scale-aware aggregation with feature alignment for one-shot object detection

Real-Time Monitoring of College Sports Dance Competition Scenes Using Deep Learning Algorithms

A Survey of Deep Learning for Low-Shot Object Detection

Contact Info

Product

Resources

About