CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal Images

Feng, Zhen; Guo, Yanning; Sun, Yuxiang

doi:10.1109/lra.2023.3247175

Cited by 17 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EdgeFormer was proposed by Wang et al [45] to promote the segmentation performance in electrical equipment's edges and interiors. CEKD [46] transfers the edge detection capability of an RGB-T teacher network to a thermal-only student network.…”

Section: Related Work 21 Single-modal Segmentationmentioning

confidence: 99%

Self-Enhanced Mixed Attention Network for Three-Modal Images Few-Shot Semantic Segmentation

Song,

Zhang,

Bao

et al. 2023

Sensors

View full text Add to dashboard Cite

As an important computer vision technique, image segmentation has been widely used in various tasks. However, in some extreme cases, the insufficient illumination would result in a great impact on the performance of the model. So more and more fully supervised methods use multi-modal images as their input. The dense annotated large datasets are difficult to obtain, but the few-shot methods still can have satisfactory results with few pixel-annotated samples. Therefore, we propose the Visible-Depth-Thermal (three-modal) images few-shot semantic segmentation method. It utilizes the homogeneous information of three-modal images and the complementary information of different modal images, which can improve the performance of few-shot segmentation tasks. We constructed a novel indoor dataset VDT-2048-5i for the three-modal images few-shot semantic segmentation task. We also proposed a Self-Enhanced Mixed Attention Network (SEMANet), which consists of a Self-Enhanced module (SE) and a Mixed Attention module (MA). The SE module amplifies the difference between the different kinds of features and strengthens the weak connection for the foreground features. The MA module fuses the three-modal feature to obtain a better feature. Compared with the most advanced methods before, our model improves mIoU by 3.8% and 3.3% in 1-shot and 5-shot settings, respectively, which achieves state-of-the-art performance. In the future, we will solve failure cases by obtaining more discriminative and robust feature representations, and explore achieving high performance with fewer parameters and computational costs.

show abstract

Section: Related Work 21 Single-modal Segmentationmentioning

confidence: 99%

Self-Enhanced Mixed Attention Network for Three-Modal Images Few-Shot Semantic Segmentation

Song,

Zhang,

Bao

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

A review of convolutional neural networks in computer vision

Zhao,

Wang,

Zhang

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

In computer vision, a series of exemplary advances have been made in several areas involving image classification, semantic segmentation, object detection, and image super-resolution reconstruction with the rapid development of deep convolutional neural network (CNN). The CNN has superior features for autonomous learning and expression, and feature extraction from original input data can be realized by means of training CNN models that match practical applications. Due to the rapid progress in deep learning technology, the structure of CNN is becoming more and more complex and diverse. Consequently, it gradually replaces the traditional machine learning methods. This paper presents an elementary understanding of CNN components and their functions, including input layers, convolution layers, pooling layers, activation functions, batch normalization, dropout, fully connected layers, and output layers. On this basis, this paper gives a comprehensive overview of the past and current research status of the applications of CNN models in computer vision fields, e.g., image classification, object detection, and video prediction. In addition, we summarize the challenges and solutions of the deep CNN, and future research directions are also discussed.

show abstract

Lightweight cross-guided contextual perceptive network for visible–infrared urban road scene parsing

Liu,

Zhou,

Fang

et al. 2024

Infrared Physics & Technology

View full text Add to dashboard Cite

CEKD: Cross-Modal Edge-Privileged Knowledge Distillation for Semantic Scene Understanding Using Only Thermal Images

Cited by 17 publications

References 28 publications

Self-Enhanced Mixed Attention Network for Three-Modal Images Few-Shot Semantic Segmentation

Self-Enhanced Mixed Attention Network for Three-Modal Images Few-Shot Semantic Segmentation

A review of convolutional neural networks in computer vision

Lightweight cross-guided contextual perceptive network for visible–infrared urban road scene parsing

Contact Info

Product

Resources

About