Výsledky vyhledávání - "Agrawal, Kshitij"

Report

Patch-wise Features for Blur Image Classification

Autor: Kattamuru, Sri Charan, Agrawal, Kshitij, Adhikari, Shyam Prasad, Bose, Abhishek, Misra, Hemant

Images captured through smartphone cameras often suffer from degradation, blur being one of the major ones, posing a challenge in processing these images for downstream tasks. In this paper we propose low-compute lightweight patch-wise features for i

Externí odkaz: http://arxiv.org/abs/2304.03156

Zobrazit plný text záznamu

Report

Meta Guided Metric Learner for Overcoming Class Confusion in Few-Shot Road Object Detection

Autor: Majee, Anay, Subramanian, Anbumani, Agrawal, Kshitij

Localization and recognition of less-occurring road objects have been a challenge in autonomous driving applications due to the scarcity of data samples. Few-Shot Object Detection techniques extend the knowledge from existing base object classes to l

Externí odkaz: http://arxiv.org/abs/2110.15074

Zobrazit plný text záznamu

Report

Few-Shot Batch Incremental Road Object Detection via Detector Fusion

Autor: Tambwekar, Anuj, Agrawal, Kshitij, Majee, Anay, Subramanian, Anbumani

Incremental few-shot learning has emerged as a new and challenging area in deep learning, whose objective is to train deep learning models using very few samples of new class data, and none of the old class data. In this work we tackle the problem of

Externí odkaz: http://arxiv.org/abs/2108.08048

Zobrazit plný text záznamu

Report

Few-Shot Learning for Road Object Detection

Autor: Majee, Anay, Agrawal, Kshitij, Subramanian, Anbumani

Few-shot learning is a problem of high interest in the evolution of deep learning. In this work, we consider the problem of few-shot object detection (FSOD) in a real-world, class-imbalanced scenario. For our experiments, we utilize the India Driving

Externí odkaz: http://arxiv.org/abs/2101.12543

Zobrazit plný text záznamu

Report

Enhancing Object Detection in Adverse Conditions using Thermal Imaging

Autor: Agrawal, Kshitij, Subramanian, Anbumani

Autonomous driving relies on deriving understanding of objects and scenes through images. These images are often captured by sensors in the visible spectrum. For improved detection capabilities we propose the use of thermal sensors to augment the vis

Externí odkaz: http://arxiv.org/abs/1909.13551

Zobrazit plný text záznamu