检索结果-内蒙古大学图书馆

Target Detection Using Transformer: A Study Using DETR

学校读者我要写书评

暂无评论

Target Detection Using Transformer: A Study Using DETR

International Conference on computer vision and Machine Intelligence, CVMI 2022

作者： Kumar, Akhilesh Singh, Satish Kumar Dubey, Shiv Ram DRDO Delhi India Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Prayagraj Allahabad India

ISBN: (纸本)9789811978661

Transformer has been proposed to augment the attention mechanism in neural networks without using recurrence and convolutions. Starting with machine translation, it graduated to vision transformer. Among the vision transformers, we explore the DEtection TRansformer (DETR) model proposed in the End-to-end Object Detection with Transformers paper by the team at Facebook AI. The authors have demonstrated interesting object detection results from the DETR model. That triggered the curiosity to use the model for detection of custom objects. Here, we are presenting the way to fine-tune the pre-trained DETR model over custom dataset. The fine-tuning results demonstrate significant improvement with respect to number of training epochs, both visibly as well as statistically. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

Transformer-based Generative Adversarial Networks in computer vision: A Comprehensive Survey

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dubey, Shiv Ram Singh, Satish Kumar The Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Prayagraj Uttar Pradesh Allahabad211015 India

Generative Adversarial Networks (GANs) have been very successful for synthesizing the images in a given dataset. The artificially generated images by GANs are very realistic. The GANs have shown potential usability in several computer vision applications, including image generation, image-to-image translation, video synthesis, and others. Conventionally, the generator network is the backbone of GANs, which generates the samples and the discriminator network is used to facilitate the training of the generator network. The discriminator network is usually a Convolutional Neural Network (CNN). Whereas, the generator network is usually either an Up-CNN for image generation or an Encoder-Decoder network for image-to-image translation. The convolution-based networks exploit the local relationship in a layer, which requires the deep networks to extract the abstract features. Hence, CNNs suffer to exploit the global relationship in the feature space. However, recently developed Transformer networks are able to exploit the global relationship at every layer. The Transformer networks have shown tremendous performance improvement for several problems in computer vision. Motivated from the success of Transformer networks and GANs, recent works have tried to exploit the Transformers in GAN framework for the image/video synthesis. This paper presents a comprehensive survey on the developments and advancements in GANs utilizing the Transformer networks for computer vision applications. The performance comparison for several applications on benchmark datasets is also performed and analyzed. The conducted survey will be very useful to deep learning and computer vision community to understand the research trends & gaps related with Transformer-based GANs and to develop the advanced GAN architectures by exploiting the global and local relationships for different applications. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

Context Unaware Knowledge Distillation for Image Retrieval 1

学校读者我要写书评

暂无评论

International Conference on computer vision and Machine Intelligence, CVMI 2022

作者： Reddy, Bytasandram Yaswanth Dubey, Shiv Ram Sanodiya, Rakesh Kumar Karn, Ravi Ranjan Prasad Department of Computer Science and Engineering Indian Institute of Information Technology Sri City Chittoor India Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Allahabad India

ISBN: (数字)9789811978678

ISBN: (纸本)9789811978661

Existing data-dependent hashing methods use large backbone networks with millions of parameters and are computationally complex. Existing knowledge distillation methods use logits and other features of the deep (teacher) model and as knowledge for the compact (student) model, which requires the teacher’s network to be fine-tuned on the context in parallel with the student model on the context. Training teacher on the target context requires more time and computational resources. In this paper, we propose context unaware knowledge distillation that uses the knowledge of the teacher model without fine-tuning it on the target context. We also propose a new efficient student model architecture for knowledge distillation. The proposed approach follows a two-step process. The first step involves pre-training the student model with the help of context unaware knowledge distillation from the teacher model. The second step involves fine-tuning the student model on the context of image retrieval. In order to show the efficacy of the proposed approach, we compare the retrieval results, no. of parameters, and no. of operations of the student models with the teacher models under different retrieval frameworks, including deep cauchy hashing (DCH) and central similarity quantization (CSQ). The experimental results confirm that the proposed approach provides a promising trade-off between the retrieval results and efficiency. The code used in this paper is released publicly at https://***/satoru2001/CUKDFIR. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Distillation

Moment Centralization-Based Gradient Descent Optimizers for Convolutional Neural Networks 1

学校读者我要写书评

暂无评论

International Conference on computer vision and Machine Intelligence, CVMI 2022

作者： Sadu, Sumanth Dubey, Shiv Ram Sreeja, S.R. Computer Vision Group Department of Computer Science and Engineering Indian Institute of Information Technology Andhra Pradesh Sri City India Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Uttar Pradesh Allahabad India Department of Computer Science and Engineering Indian Institute of Information Technology Andhra Pradesh Sri City India

ISBN: (数字)9789811978678

ISBN: (纸本)9789811978661

Convolutional neural networks (CNNs) have shown very appealing performance for many computer vision applications. The training of CNNs is generally performed using stochastic gradient descent (SGD)-based optimization techniques. The adaptive momentum-based SGD optimizers are the recent trends. However, the existing optimizers are not able to maintain a zero mean in the first order moment and struggle with optimization. In this paper, we propose a moment centralization-based SGD optimizer for CNNs. Specifically, we impose the zero mean constraints on the first order moment explicitly. The proposed moment centralization is generic in nature and can be integrated with any of the existing adaptive momentum-based optimizers. The proposed idea is tested with three state-of-the-art optimization techniques, including Adam, Radam, and Adabelief on benchmark CIFAR10, CIFAR100, and TinyImageNet datasets for image classification. The performance of the existing optimizers is generally improved when integrated with the proposed moment centralization. Further, the results of the proposed moment centralization are also better than the existing gradient centralization. The analytical analysis using the toy example shows that the proposed method leads to a shorter and smoother optimization trajectory. The source code is made publicly available at https://***/sumanthsadhu/MC-optimizer. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Optimization

Segmentation of Hard Exudates And Hemorrhages from Diabetic Retinopathy Images Using Residual U-Net with Squeeze and Excite Blocks

学校读者我要写书评

暂无评论

Segmentation of Hard Exudates And Hemorrhages from Diabetic ...

IEEE International Conference on Image Processing

作者： Avinash Gaikwad Anjali Gautam Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Allahabad Prayagraj Uttar Pradesh INDIA

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Diabetic Retinopathy (DR) is a common eye disease worldwide and usually found in diabetes patients. Deep learning based algorithms have recently produced promising findings for the automatic detection and segmentation of DR lesions from fundus images. In this paper, we present an approach for segmenting DR using a Residual U-Net model. Here, we have incorporated Squeeze and Excite (SE) blocks into the Residual U-Net architecture to segment various DR diseases from fundus images. SE blocks are attention techniques that dynamically recalibrate the feature maps of a neural network. These enable the network to prioritize useful features while suppressing less important ones, hence boosting the model’s ability to discriminate. We intended to enhance the segmentation performance by enabling the model to better capture spatial and contextual information by integrating SE blocks into the Residual U-Net architecture. The developed model architecture was trained and tested on fundus image DR datasets. The results obtained by the developed model for hard exudates and hemorrhages segmentations were better as compared to U-Net and its variants.

关键词： Training Deep learning Image segmentation Diabetic retinopathy Neural networks Eye diseases Boosting

Context Unaware Knowledge Distillation for Image Retrieval

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Reddy, Bytasandram Yaswanth Dubey, Shiv Ram Sanodiya, Rakesh Kumar Karn, Ravi Ranjan Prasad Department of Computer Science and Engineering Indian Institute of Information Technology Chittoor Sri City India Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Allahabad India

Existing data-dependent hashing methods use large backbone networks with millions of parameters and are computationally complex. Existing knowledge distillation methods use logits and other features of the deep (teacher) model and as knowledge for the compact (student) model, which requires the teacher’s network to be fine-tuned on the context in parallel with the student model on the context. Training teacher on the target context requires more time and computational resources. In this paper, we propose context unaware knowledge distillation that uses the knowledge of the teacher model without fine-tuning it on the target context. We also propose a new efficient student model architecture for knowledge distillation. The proposed approach follows a two-step process. The first step involves pre-training the student model with the help of context unaware knowledge distillation from the teacher model. The second step involves fine-tuning the student model on the context of image retrieval. In order to show the efficacy of the proposed approach, we compare the retrieval results, no. of parameters and no. of operations of the student models with the teacher models under different retrieval frameworks, including deep cauchy hashing (DCH) and central similarity quantization (CSQ). The experimental results confirm that the proposed approach provides a promising trade-off between the retrieval results and efficiency. The code used in this paper is released publicly at https://***/satoru2001/CUKDFIR. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

TVA-GAN: Attention Guided Generative Adversarial Network For Thermal To Visible Image Transformations

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Yadav, Nand Kumar Singh, Satish Kumar Dubey, Shiv Ram The Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Allahabad211015 India

In the recent advancement of machine learning methods for realistic image generation and image translation, Generative Adversarial Networks (GANs) play a vital role. GAN generates novel samples that look indistinguishable from the real images. The image translation using a generative adversarial network refers to unsupervised learning. In this paper, we translate the thermal images into visible images. Thermal to Visible image translation is challenging due to the non-availability of accurate semantic information and smooth textures. The thermal images contain only single-channel, holding only the images’ luminance with less feature. We develop a new Cyclic Attention-based Generative Adversarial Network for Thermal to Visible domain transformation (TVA-GAN) by incorporating a new attention-based network. We use attention guidance with a recurrent block through an Inception module to reduce the learning space towards the optimum solution. TVA-GAN is tested and evaluated for thermal to visible face synthesis over the WHU-IIP and Tufts Face Thermal2RGB datasets. The results using the proposed TVA-GAN is promising for face synthesis as compared to the state-of-the-art GAN methods. © 2021, CC BY.

关键词： Generative adversarial networks

HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sarvani, C.H. Ghorai, Mrinmoy Dubey, Shiv Ram Basha, S.H. Shabbeer Computer Vision Group Indian Institute of Information Technology Sri City Andhra Pradesh Chittoor517646 India Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Uttar Pradesh Allahabad211015 India DryvAmigo Karnataka Banglore India

This paper proposes an Information Bottleneck theory based filter pruning method that uses a statistical measure called Mutual Information (MI). The MI between filters and class labels, also called Relevance, is computed using the filter's activation maps and the annotations. The filters having High Relevance (HRel) are considered to be more important. Consequently, the least important filters, which have lower Mutual Information with the class labels, are pruned. Unlike the existing MI based pruning methods, the proposed method determines the significance of the filters purely based on their corresponding activation map's relationship with the class labels. Architectures such as LeNet-5, VGG-16, ResNet-56, ResNet-110 and ResNet-50 are utilized to demonstrate the efficacy of the proposed pruning method over MNIST, CIFAR-10 and ImageNet datasets. The proposed method shows the state-of-the-art pruning results for LeNet-5, VGG-16, ResNet-56, ResNet-110 and ResNet-50 architectures. In the experiments, we prune 97.98 %, 84.85 %, 76.89%, 76.95%, and 63.99% of Floating Point Operation (FLOP)s from LeNet-5, VGG-16, ResNet-56, ResNet-110, and ResNet-50 respectively. The proposed HRel pruning method outperforms recent state-of-the-art filter pruning methods. Even after pruning the filters from convolutional layers of LeNet-5 drastically (i.e., from 20, 50 to 2, 3, respectively), only a small accuracy drop of 0.52% is observed. Notably, for VGG-16, 94.98% parameters are reduced, only with a drop of 0.36% in top-1 accuracy. ResNet-50 has shown a 1.17% drop in the top-5 accuracy after pruning 66.42% of the FLOPs. In addition to pruning, the Information Plane dynamics of Information Bottleneck theory is analyzed for various Convolutional Neural Network architectures with the effect of pruning. The code is available at https://***/sarvanichinthapalli/HRel. This paper is published by Neural Networks, Elsevier. The final paper is available at: https://***/sc

关键词： Convolution

Moment Centralization based Gradient Descent Optimizers for Convolutional Neural Networks

学校读者我要写书评

暂无评论

arXiv 2022年

Convolutional neural networks (CNNs) have shown very appealing performance for many computer vision applications. The training of CNNs is generally performed using stochastic gradient descent (SGD) based optimization techniques. The adaptive momentum-based SGD optimizers are the recent trends. However, the existing optimizers are not able to maintain a zero mean in the first-order moment and struggle with optimization. In this paper, we propose a moment centralization-based SGD optimizer for CNNs. Specifically, we impose the zero mean constraints on the first-order moment explicitly. The proposed moment centralization is generic in nature and can be integrated with any of the existing adaptive momentum-based optimizers. The proposed idea is tested with three state-of-the-art optimization techniques, including Adam, Radam, and Adabelief on benchmark CIFAR10, CIFAR100, and TinyImageNet datasets for image classification. The performance of the existing optimizers is generally improved when integrated with the proposed moment centralization. Further, The results of the proposed moment centralization are also better than the existing gradient centralization. The analytical analysis using the toy example shows that the proposed method leads to a shorter and smoother optimization trajectory. The source code is made publicly available at https://***/sumanthsadhu/MC-optimizer. Copyright © 2022, The Authors. All rights reserved.

关键词： Optimization