Solving the Domain Shift Problem in Deep Learning

2023.02.27
464

Subject

Solving the Domain Shift Problem in Deep Learning

Date

2023.02.27(Mon.) 16:00~17:30

Speaker

Dr. Seokeon Choi (Qualcomm Korea)

Place

Kim Beang-Ho & Kim Sam-Youl ITC Building(N1) #102

Overview:

O Topic : Solving the Domain Shift Problem in Deep Learning

O Speaker: Dr. Seokeon Choi (Qualcomm Korea)

O Date: 2023.02.27(Mon.)

O Start Time: 16:00

O Venue: N1. #102

O Abstract:

Deep learning has made remarkable advancements in various computer vision tasks, such as object recognition, detection, segmentation, and person re-identification. However, the performance of these models can deteriorate when they are applied to new domains with different distributions or characteristics than the data they were trained on. This is known as the domain shift problem and can pose a significant challenge in real-world scenarios, particularly in defense and security applications. In this talk, I will briefly present my research on addressing the domain shift problem through feature disentanglement, meta-learning, image augmentation, and regularization techniques.

Profile:

–

News & Event

Seminar

Notice

Calendar

Seminar

Event

Press

Job Openings

Newsletter

Solving the Domain Shift Problem in Deep Learning

Subject