A more compact object detector head network with feature enhancement and relational reasoning

Zhang, Wen chao; Fu, Chong; Chang, Xiang; Zhao, Teng; Li, Xiang; Sham, Chiu-Wing

doi:10.1016/j.neucom.2022.05.034

Cited by 15 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The COCO dataset is among the most widely used and comprehensive datasets for object recognition and other computer vision tasks [13,16,41]. Researchers often use the COCO dataset as a testbed for developing and testing models related to object recognition, instance segmentation, and image captioning.…”

Section: Introductionmentioning

confidence: 99%

Color Face Image Generation with Improved Generative Adversarial Networks

Chang,

Chung,

Chai

et al. 2024

Electronics

View full text Add to dashboard Cite

This paper focuses on the development of an improved Generative Adversarial Network (GAN) specifically designed for generating color portraits from sketches. The construction of the system involves using a GPU (Graphics Processing Unit) computing host as the primary unit for model training. The tasks that require high-performance calculations are handed over to the GPU host, while the user host only needs to perform simple image processing and use the model trained by the GPU host to generate images. This arrangement reduces the computer specification requirements for the user. This paper will conduct a comparative analysis of various types of generative networks which will serve as a reference point for the development of the proposed Generative Adversarial Network. The application part of the paper focuses on the practical implementation and utilization of the developed Generative Adversarial Network for the generation of multi-skin tone portraits. By constructing a face dataset specifically designed to incorporate information about ethnicity and skin color, this approach can overcome a limitation associated with traditional generation networks, which typically generate only a single skin color.

show abstract

Section: Introductionmentioning

confidence: 99%

Color Face Image Generation with Improved Generative Adversarial Networks

Chang,

Chung,

Chai

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning-based approaches [ 8 ] have been widely applied to histopathology image analysis, achieving remarkable results. In [ 9 ], Xu et al, proposed a deep learning method based on convolutional neural networks (CNNs) to automatically segment and classify epithelial and stromal regions in histopathology images.…”

Section: Introductionmentioning

confidence: 99%

RGSB-UNet: Hybrid Deep Learning Framework for Tumour Segmentation in Digital Pathology Images

Zhao

Tie³

et al. 2023

Bioengineering

Self Cite

View full text Add to dashboard Cite

Colorectal cancer (CRC) is a prevalent gastrointestinal tumour with high incidence and mortality rates. Early screening for CRC can improve cure rates and reduce mortality. Recently, deep convolution neural network (CNN)-based pathological image diagnosis has been intensively studied to meet the challenge of time-consuming and labour-intense manual analysis of high-resolution whole slide images (WSIs). Despite the achievements made, deep CNN-based methods still suffer from some limitations, and the fundamental problem is that they cannot capture global features. To address this issue, we propose a hybrid deep learning framework (RGSB-UNet) for automatic tumour segmentation in WSIs. The framework adopts a UNet architecture that consists of the newly-designed residual ghost block with switchable normalization (RGS) and the bottleneck transformer (BoT) for downsampling to extract refined features, and the transposed convolution and 1 × 1 convolution with ReLU for upsampling to restore the feature map resolution to that of the original image. The proposed framework combines the advantages of the spatial-local correlation of CNNs and the long-distance feature dependencies of BoT, ensuring its capacity of extracting more refined features and robustness to varying batch sizes. Additionally, we consider a class-wise dice loss (CDL) function to train the segmentation network. The proposed network achieves state-of-the-art segmentation performance under small batch sizes. Experimental results on DigestPath2019 and GlaS datasets demonstrate that our proposed model produces superior evaluation scores and state-of-the-art segmentation results.

show abstract

Cross-scale Dynamic Relation Network for Object Detection

Zhong,

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A more compact object detector head network with feature enhancement and relational reasoning

Cited by 15 publications

References 47 publications

Color Face Image Generation with Improved Generative Adversarial Networks

Color Face Image Generation with Improved Generative Adversarial Networks

RGSB-UNet: Hybrid Deep Learning Framework for Tumour Segmentation in Digital Pathology Images

Cross-scale Dynamic Relation Network for Object Detection

Contact Info

Product

Resources

About