Search Results for author:
Found 30 papers, 15 papers with code
Class Distance Weighted Cross Entropy Loss for Classification of Disease Severity
Its performance was compared against several categorical and ordinal loss functions.
Augmentation Policy Generation for Image Classification Using Large Language Models
Automated data augmentation methods have significantly improved the performance and generalization capability of deep learning models in image classification.
TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problem
Recently, the centerline has become a popular representation of lanes due to its advantages in solving the road topology problem.
Ranked #2 on
3D Lane Detection
on OpenLane-V2 val
State-of-the-Art in Nudity Classification: A Comparative Analysis
This paper presents a comparative analysis of existing nudity classification techniques for classifying images based on the presence of nudity, with a focus on their application in content moderation.
Ulcerative Colitis Mayo Endoscopic Scoring Classification with Active Learning and Generative Data Augmentation
The method involves generating a large number of synthetic samples by training using a small dataset consisting of real endoscopic images.
Adversarial Image Generation by Spatial Transformation in Perceptual Colorspaces
Deep neural networks are known to be vulnerable to adversarial perturbations.
TopoMask: Instance-Mask-Based Formulation for the Road Topology Problem via Transformer-Based Architecture
In this study, we have introduced a new approach called TopoMask for predicting centerlines in road topology.
Ranked #1 on
3D Lane Detection
on OpenLane-V2 test
Deep Architectures for Content Moderation and Movie Content Rating
Rating a video based on its content is an important step for classifying video age categories.
Improving the Computer-Aided Estimation of Ulcerative Colitis Severity According to Mayo Endoscopic Score by Using Regression-Based Deep Learning
We propose a regression-based deep learning approach for the endoscopic evaluation of UC according to the Mayo endoscopic score (MES).
Ranked #2 on
Image Classification
on LIMUC
Sequence Models for Drone vs Bird Classification
Moreover, we propose a new drone vs. bird sequence classification dataset to train and evaluate the proposed architectures.
Evaluation and Analysis of Different Aggregation and Hyperparameter Selection Methods for Federated Brain Tumor Segmentation
Availability of large, diverse, and multi-national datasets is crucial for the development of effective and clinically applicable AI systems in the medical imaging domain.
Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection
In this work, an open-source framework called Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection.
Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity Estimation
Experimental evaluations show that models trained with CDW-CE outperform the models trained with conventional categorical cross-entropy and other commonly used loss functions which are designed for the ordinal regression problems.
Ranked #1 on
Image Classification
on LIMUC
Training Universal Adversarial Perturbations with Alternating Loss Functions
Despite being very successful, deep learning models were shown to be vulnerable to crafted perturbations.
Improving Perceptual Quality of Adversarial Images Using Perceptual Distance Minimization and Normalized Variance Weighting
We show that these methods could also be used in conjunction to improve the perceptual quality of adversarial examples and demonstrate the quantitative improvements on CIFAR-10 and NIPS2017 Adversarial Learning Challenge datasets.
Automated question generation and question answering from Turkish texts
In this work, we fine-tune a multilingual T5 (mT5) transformer in a multi-task setting for QA, QG and answer extraction tasks using Turkish QA datasets.
Imperceptible Adversarial Examples by Spatial Chroma-Shift
Deep Neural Networks have been shown to be vulnerable to various kinds of adversarial perturbations.
Generative Data Augmentation for Vehicle Detection in Aerial Images
The experiments show that the method increases the Average Precision by up to 25. 2% and 25. 7% when integrated with Pluralistic and DeepFill respectively.
Deep learning for detection and segmentation of artefact and disease instances in gastrointestinal endoscopy
The Endoscopy Computer Vision Challenge (EndoCV) is a crowd-sourcing initiative to address eminent problems in developing reliable computer aided detection and diagnosis endoscopy systems and suggest a pathway for clinical translation of technologies.
LPMNet: Latent Part Modification and Generation for 3D Point Clouds
In this paper, we focus on latent modification and generation of 3D point cloud object models with respect to their semantic parts.
Performance Analysis of Noise Subspace-based Narrowband Direction-of-Arrival (DOA) Estimation Algorithms on CPU and GPU
High-performance computing of array signal processing problems is a critical task as real-time system performance is required for many applications.
Distributed, Parallel, and Cluster Computing Signal Processing
Optimization of XNOR Convolution for Binary Convolutional Neural Networks on GPU
Binary convolutional networks have lower computational load and lower memory foot-print compared to their full-precision counterparts.
Bit-level Parallelization of 3DES Encryption on GPU
Triple DES (3DES) is a standard fundamental encryption algorithm, used in several electronic payment applications and web browsers.
Cryptography and Security Distributed, Parallel, and Cluster Computing
Accelerating Translational Image Registration for HDR Images on GPU
High Dynamic Range (HDR) images are generated using multiple exposures of a scene.
Speaker and Posture Classification using Instantaneous Intraspeech Breathing Features
Instantaneous magnitude features are extracted using the Hilbert-Huang transform (HHT) and fed into a CNN-GRU network for classification of recordings from the open intraspeech breathing sound dataset, BreathBase, that we collected for this study.
Attack Type Agnostic Perceptual Enhancement of Adversarial Images
Adversarial images are samples that are intentionally modified to deceive machine learning systems.
Paired 3D Model Generation with Conditional Generative Adversarial Networks
Generative Adversarial Networks (GANs) are shown to be successful at generating new and realistic samples including 3D object models.
Multi-modal Egocentric Activity Recognition using Audio-Visual Features
In this work, we propose a new framework for egocentric activity recognition problem based on combining audio-visual features with multi-kernel learning (MKL) and multi-kernel boosting (MKBoost).
The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examples
To be immune to such attacks, it is desirable to have a pre-processing mechanism which removes these effects causing misclassification while keeping the content of the image.
Boosted Multiple Kernel Learning for First-Person Activity Recognition
Activity recognition from first-person (ego-centric) videos has recently gained attention due to the increasing ubiquity of the wearable cameras.
