Search Results for author:
Found 54 papers, 25 papers with code
Transformer-based Clipped Contrastive Quantization Learning for Unsupervised Image Retrieval
Unsupervised image retrieval aims to learn the important visual characteristics without any given level to retrieve the similar images for a given query image.
Face to Cartoon Incremental Super-Resolution using Knowledge Distillation
Facial super-resolution/hallucination is an important area of research that seeks to enhance low-resolution facial images for a variety of applications.
SRTransGAN: Image Super-Resolution using Transformer based Generative Adversarial Network
Motivated from the success of transformers in language and vision applications, we propose a SRTransGAN for image super-resolution using transformer based GAN.
PTSR: Patch Translator for Image Super-Resolution
The results of the proposed model is improved on an average for $4\times$ super-resolution by 21. 66% in PNSR score and 11. 59% in SSIM score, as compared to the best competitive models.
Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey
This paper presents a comprehensive survey on the developments and advancements in GANs utilizing the Transformer networks for computer vision applications.
WSD: Wild Selfie Dataset for Face Recognition in Selfie Images
In order to alleviate this problem and to facilitate the research on selfie face images, we develop a challenging Wild Selfie Dataset (WSD) where the images are captured from the selfie cameras of different smart phones, unlike existing datasets where most of the images are captured in controlled environment.
EMAHA-DB1: A New Upper Limb sEMG Dataset for Classification of Activities of Daily Living
The state-of-theart classification accuracy on five FAABOS categories is 83:21% by using the SVM classifier with the third order polynomial kernel using energy feature and auto regressive feature set ensemble.
AdaNorm: Adaptive Gradient Norm Correction based Optimizer for CNNs
In this paper, we propose a novel AdaNorm based SGD optimizers by correcting the norm of gradient in each iteration based on the adaptive training history of gradient norm.
T2CI-GAN: Text to Compressed Image generation using Generative Adversarial Network
The first model is directly trained with JPEG compressed DCT images (compressed domain) to generate the compressed images from text descriptions.
Context Unaware Knowledge Distillation for Image Retrieval
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.
Moment Centralization based Gradient Descent Optimizers for Convolutional Neural Networks
However, the existing optimizers are not able to maintain a zero mean in the first-order moment and struggle with optimization.
Target Aware Network Architecture Search and Compression for Efficient Knowledge Transfer
Later, in the second stage, the redundant filters are pruned from the fine-tuned CNN to decrease the network's complexity for the target task while preserving the performance.
HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels
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.
HWRCNet: Handwritten Word Recognition in JPEG Compressed Domain using CNN-BiLSTM Network
Handwritten word recognition from document images using deep learning is an active research area in the field of Document Image Analysis and Recognition.
Semantic Map Injected GAN Training for Image-to-Image Translation
Specifically, we train with original input and output modalities and inject a few epochs of training for translation from input to semantic map.
Generative Adversarial Network
Image-to-Image Translation
+2
Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark
The most popular and common non-linearity layers are activation functions (AFs), such as Logistic Sigmoid, Tanh, ReLU, ELU, Swish and Mish.
Frequency Disentangled Residual Network
Moreover, the computation of low and high frequency components using fixed filters further avoids the overfitting.
AdaInject: Injection Based Adaptive Gradient Descent Optimizers for Convolutional Neural Networks
Overall, we observe very promising performance improvement of existing optimizers with the proposed AdaInject approach.
Vision Transformer Hashing for Image Retrieval
We utilize the pre-trained ViT on ImageNet as the backbone network and add the hashing head.
Efficient High-Resolution Image-to-Image Translation using Multi-Scale Gradient U-Net
We provide the code of MSG U-Net model at https://github. com/laxmaniron/MSG-U-Net.
Generative Adversarial Network
Image-to-Image Translation
+1
Joint Triplet Autoencoder for Histopathological Colon Cancer Nuclei Retrieval
A joint supervised learning for Siamese network and unsupervised learning for Autoencoder is performed.
AC-CovidNet: Attention Guided Contrastive CNN for Recognition of Covid-19 in Chest X-Ray Images
Chest X-Ray (CXR) testing can be a fast, scalable, and non-invasive method.
Generative Adversarial Minority Oversampling for Spectral-Spatial Hyperspectral Image Classification
A different classifier from the generator and the discriminator is used in the 3D-HyperGAMO model, which is trained using both original and generated samples to {determine} the classes of newly generated samples to which they actually belong.
Deep Model Compression based on the Training History
First, we train the model and select the filter pairs with redundant filters in each pair.
Color Channel Perturbation Attacks for Fooling Convolutional Neural Networks and A Defense Against Such Attacks
It is widely used in several computer vision problems.
MERANet: Facial Micro-Expression Recognition using 3D Residual Attention Network
The proposed model takes advantage of spatial-temporal attention and channel attention together, to learn deeper fine-grained subtle features for classification of emotions.
A Decade Survey of Content Based Image Retrieval using Deep Learning
The categorization of existing state-of-the-art methods from different perspectives is also performed for greater understanding of the progress.
On the Performance of Convolutional Neural Networks under High and Low Frequency Information
In this letter, we study the performance of CNN models over the high and low frequency information of the images.
AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning
The experimental results obtained in this study depict that tuning of the pre-trained CNN layers with the knowledge from the target dataset confesses better transfer learning ability.
PCSGAN: Perceptual Cyclic-Synthesized Generative Adversarial Networks for Thermal and NIR to Visible Image Transformation
However, the images can be captured in such scenarios using Near-Infrared (NIR) and Thermal (THM) cameras.
AutoFCL: Automatically Tuning Fully Connected Layers for Handling Small Dataset
Fine-tuning the newly learned (target-dependent) FC layers leads to state-of-the-art performance, according to the experiments carried out in this research.
CDGAN: Cyclic Discriminative Generative Adversarial Networks for Image-to-Image Transformation
The proposed CDGAN method outperforms the state-of-the-art methods when compared over the three baseline Image-to-Image transformation datasets.
PSNet: Parametric Sigmoid Norm Based CNN for Face Recognition
It is also used over widely studied face recognition problem.
NASIB: Neural Architecture Search withIn Budget
Neural Architecture Search (NAS) represents a class of methods to generate the optimal neural network architecture and typically iterate over candidate architectures till convergence over some particular metric like validation loss.
diffGrad: An Optimization Method for Convolutional Neural Networks
In this paper, a novel optimizer is proposed based on the difference between the present and the immediate past gradient (i. e., diffGrad).
Visual Question Answering using Deep Learning: A Survey and Performance Analysis
The Visual Question Answering (VQA) task combines challenges for processing data with both Visual and Linguistic processing, to answer basic `common sense' questions about given images.
Hard-Mining Loss based Convolutional Neural Network for Face Recognition
Various loss functions such as Cross-Entropy, Angular-Softmax and ArcFace have been introduced to learn the weights of network for face recognition.
Spontaneous Facial Micro-Expression Recognition using 3D Spatiotemporal Convolutional Neural Networks
This paper proposes two 3D-CNN methods: MicroExpSTCNN and MicroExpFuseNet, for spontaneous facial micro-expression recognition by exploiting the spatiotemporal information in CNN framework.
Facial Expression Recognition
Micro Expression Recognition
+1
HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification
This letter proposes a Hybrid Spectral Convolutional Neural Network (HybridSN) for HSI classification.
Ranked #1 on
Hyperspectral Image Classification
on Salinas Scene
Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification
To automate the process of learning a CNN architecture, this paper attempts at finding the relationship between Fully Connected (FC) layers with some of the characteristics of the datasets.
CSGAN: Cyclic-Synthesized Generative Adversarial Networks for Image-to-Image Transformation
Most of the research focuses over the suitable objective function for image-to-image transformation.
LiSHT: Non-Parametric Linearly Scaled Hyperbolic Tangent Activation Function for Neural Networks
The proposed LiSHT is non-parametric and tackles the dying gradient problem.
A Performance Comparison of Loss Functions for Deep Face Recognition
Face recognition is one of the most widely publicized feature in the devices today and hence represents an important problem that should be studied with the utmost priority.
RCCNet: An Efficient Convolutional Neural Network for Histological Routine Colon Cancer Nuclei Classification
The results of the proposed RCCNet model are compared with five state-of-the-art CNN models in terms of the accuracy, weighted average F1 score and training time.
A Multi-Face Challenging Dataset for Robust Face Recognition
Multiple face recognition in unconstrained environment is a challenging task, due to the variation of view-point, scale, pose, illumination and expression of the face images.
A Performance Evaluation of Convolutional Neural Networks for Face Anti Spoofing
Precise detection of spoofed faces should be on the high priority to make face based identity recognition and access control robust against possible attacks.
Dual CNN Models for Unsupervised Monocular Depth Estimation
The unsupervised depth estimation is the recent trend by utilizing the binocular stereo images to get rid of depth map ground truth.
Average Biased ReLU Based CNN Descriptor for Improved Face Retrieval
It is observed that the AB-ReLU outperforms the ReLU when used with a pre-trained VGGFace model over the face datasets.
LDOP: Local Directional Order Pattern for Robust Face Retrieval
The proposed local directional order pattern (LDOP) for a particular pixel is computed by finding the relationship between the center pixel and local directional order indexes.
Local Jet Pattern: A Robust Descriptor for Texture Classification
In this approach, a jet space representation of a texture image is derived from a set of derivatives of Gaussian (DtGs) filter responses up to second order, so called local jet vectors (LJV), which also satisfy the Scale Space properties.
Local Directional Relation Pattern for Unconstrained and Robust Face Retrieval
Very promising performance is observed using the proposed descriptor over very appealing face databases as compared to the existing face descriptors.
Face Retrieval using Frequency Decoded Local Descriptor
In order to increase the discriminative power of the local descriptors, some researchers converted the raw image into multiple images with the help of some high and low pass frequency filters, then the local descriptors are computed over each filtered image and finally concatenated into a single descriptor.
Fusing Color and Texture Cues to Categorize the Fruit Diseases from Images
The economic and production losses in agricultural industry worldwide are due to the presence of diseases in the several kinds of fruits.
Adapted Approach for Fruit Disease Identification using Images
Diseases in fruit cause devastating problem in economic losses and production in agricultural industry worldwide.
