DataHour: Deep Dive into Semantic Segmentation- Techniques, Challenges and State-of-the-Art

DataHour Recording

Find the resources used in the DataHour HERE.

About the DataHour:

Semantic segmentation is a critical task in computer vision, where the goal is to assign a semantic label to each pixel in an image. It has a wide range of applications, including medical imaging, autonomous vehicles, and scene understanding. In this DataHour, Kashish will provide you with a deep understanding of the techniques, challenges, and state-of-the-art developments in semantic segmentation.

You will also learn about the different types of deep learning techniques used in semantic segmentation, including neural network architectures, loss functions, data pre-processing and augmentation techniques. You will be introduced to the challenges involved in semantic segmentation and ways to address them. Finally, he will explain the state-of-the-art models and their performance on benchmark datasets, as well as the applications of semantic segmentation in various domains.

Prerequisites: Basic knowledge of Deep learning, Programming skills in Python and familiarity with popular deep learning frameworks such as TensorFlow or PyTorch and most importantly curiosity of learning about computer vision and deep learning.

Who is this DataHour for?

• Students & Freshers who want to build a career in the Data-tech domain.
• Working professionals who want to transition to the Data-tech domain.
• Data science professionals who want to accelerate their career growth

Note: E-certificates will be provided within 24 - 48 hours of the session only to those who have attended the entire webinar. Please make sure to join the zoom webinar with your correct name and email address to ensure that your certificate is properly credited to you.

Speaker:

Kashish Nagpal

Senior Data Scientist at Airtel Africa Digital Labs

Kashish is a Senior Data Scientist with 4 years of experience in the field. He is currently working with Airtel Africa Digital Labs, leveraging his expertise to drive innovation and deliver impactful solutions. He mainly focuses on computer vision, with a particular emphasis on object detection and semantic segmentation. He has also worked on complex problems such as authentication systems, including fingerprint recognition and speaker verification. With experience in MLOps and a successful track record of model deployment and data pipeline creation, he brings a well-rounded approach to his work, and is always eager to explore new developments in Artificial Intelligence. His goal is to continue making a meaningful impact in the industry.

You can connect with him on Linkedin.