The Ikshana Hypothesis of Human Scene Understanding

Daliparthi, Venkata Satya Sai Ajay

doi:10.1007/978-981-19-4136-8_12

Cited by 5 publications

(4 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the repeated convolutions and down‐sampling operations, it may lead to the loss of details, and the deep layer of CNN cannot fully capture efficient contextual information of features [46]. Inspired by the idea of the dual‐branch network [47], we introduce a lightweight dense flow branch to further enrich the high‐level semantic information, as shown in Figure 4.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive learning Unet‐based adversarial network with CNN and transformer for segmentation of hard exudates in diabetes retinopathy

Zhang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Accurate segmentation of hard exudates in early non‐proliferative diabetic retinopathy can assist physicians in taking appropriate treatment in a more targeted manner, in order to avoid more serious damage to vision caused by the deterioration of the disease in the later stages. Here, an Adaptive Learning Unet‐based adversarial network with Convolutional neural network and Transformer (CT‐ALUnet) is proposed for automatic segmentation of hard exudates, combining the excellent local modelling ability of Unet with the global attention mechanism of transformer. Firstly, multi‐scale features are extracted through a CNN dual‐branch encoder. Then, the information fusion of features at adjacent scale is realized and the fused features are selected adaptively to maintain the overall consistency of features by attention‐guided multi‐scale fusion blocks (AGMFB). After that, the high‐level encoded features are input to transformer blocks to extract global contexts. Finally, these features are fused layer‐by‐layer to achieve accurate segmentation of hard exudates. In addition, adversarial training is incorporated into the above segmentation model, which improves Dice scores and MIoU scores by 7.5% and 3%, respectively. Experiments demonstrate that CT‐ALUnet shows more reliable segmentation and stronger generalization ability than other SOTA methods, which lays a good foundation for computer‐assisted diagnosis and assessment of efficacy.

show abstract

Section: Methodsmentioning

confidence: 99%

“…We compare our proposed CT‐ALUnet with seven methods based on deep learning: DeeplabV3+ [53], PDFnet [46], Unet++ [16], TransUnet [26], Hednet+cGAN [38], Bin [9], and PMCnet [48]. The first two methods are originally designed for natural scene image segmentation and the rest are used for medical image segmentation.…”

Section: Methodsmentioning

confidence: 99%

Adaptive learning Unet‐based adversarial network with CNN and transformer for segmentation of hard exudates in diabetes retinopathy

Zhang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Thus, they proposed a new context-guided block to learn the local feature and the surrounding context which makes encouraging results. More recently, Daliparthi [13] proposed a new CNN named IkshanaNet, which is inspired by the human brain. However, this work did not achieve good results in terms of precision and parameters requirements.…”

Section: Related Workmentioning

confidence: 99%

Efficient lightweight residual network for real-time road semantic segmentation

Kherraki

Maqbool²,

Ouazzani

2023

IJ-AI

View full text Add to dashboard Cite

<span lang="EN-US">Intelligent transportation system (ITS) is currently one of the most discussed topics in scientific research. Actually, ITS offers advanced monitoring systems that include vehicle counting, pedestrian detection. Lately, convolutional neural networks (CNNs) are extensively used in computer vision tasks, including segmentation, classification, and detection. In fact, image semantic segmentation is a critical issue in computer vision applications. For example, self-driving vehicles require high accuracy with lower parameter requirements to segment the road scene objects in real-time. However, most related work focus on one side, accuracy or parameter requirements, which make CNN models difficult to use in real-time applications. In order to resolve this issue, we propose the efficient lightweight residual network (ELRNet), a novel and ELRNet, which is an asymmetrical encoder-decoder architecture. Indeed, in this network, we compare four varieties of the proposed factorized block, and three loss functions to get the best combination. In addition, the proposed model is trained from scratch using only 0.61M parameters. All experiments are evaluated on the popular public the cambridge-driving labeled video database (CamVid) road scene dataset and reached results show that ELRNet can achieve better performance in terms of parameters requirements and precision compared to related work.</span>

show abstract

“…This work achieves encouraging results. According to [15], a CNN inspired by the human brain called IkshanaNet, has been proposed. However, this network did not yield satisfactory results in terms of precision and parameter requirements.…”

Section: Related Workmentioning

confidence: 99%

Residual balanced attention network for real-time traffic scene semantic segmentation

Kherraki

Warraich²,

Maqbool³

et al. 2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Intelligent transportation systems (ITS) are among the most focused research in this century. Actually, autonomous driving provides very advanced tasks in terms of road safety monitoring which include identifying dangers on the road and protecting pedestrians. In the last few years, deep learning (DL) approaches and especially convolutional neural networks (CNNs) have been extensively used to solve ITS problems such as traffic scene semantic segmentation and traffic signs classification. Semantic segmentation is an important task that has been addressed in computer vision (CV). Indeed, traffic scene semantic segmentation using CNNs requires high precision with few computational resources to perceive and segment the scene in real-time. However, we often find related work focusing only on one aspect, the precision, or the number of computational parameters. In this regard, we propose RBANet, a robust and lightweight CNN which uses a new proposed balanced attention module, and a new proposed residual module. Afterward, we have simulated our proposed RBANet using three loss functions to get the best combination using only 0.74M parameters. The RBANet has been evaluated on CamVid, the most used dataset in semantic segmentation, and it has performed well in terms of parameters’ requirements and precision compared to related work.</span>

show abstract

The Ikshana Hypothesis of Human Scene Understanding

Cited by 5 publications

References 82 publications

Adaptive learning Unet‐based adversarial network with CNN and transformer for segmentation of hard exudates in diabetes retinopathy

Adaptive learning Unet‐based adversarial network with CNN and transformer for segmentation of hard exudates in diabetes retinopathy

Efficient lightweight residual network for real-time road semantic segmentation

Residual balanced attention network for real-time traffic scene semantic segmentation

Contact Info

Product

Resources

About