Moon Ye-Bin

Propose to utilize synthetic data to address three distinctive data imbalance problems

[Workshop] ICCVw 2023 (MMFM: What is Next in Multimodal Foundation Models?)

We propose an eye examination process to investigate how a VLM perceives images, specifically focusing on key elements of visual recognition, from primitive color and shape to semantic levels.

The key idea of our BEAF benchmark is manipulating visual scene information and designing the metrics based on the model's answer changes along the scene changes.

Propose a text-driven manifold augmentation method that semantically enriches visual feature spaces, regardless of data distribution

[Workshop] CVPRw 2023 (WFM: Workshop on Foundation Models)

[Workshop] ICCVw 2023 (MMFM: What is Next in Multimodal Foundation Models?)

Proposed ENInst with sub-task enhancement methods: instance-wise refinement for enhancing pixel localization quality and novel classifier composition for improving classification accuracy, based on the performance bottleneck analyses

[Conference] IPIU 2022, Best Paper Award

Propose High Dynamic Range Plenoxels (HDR-Plenoxels) that learns the plenoptic function of the 3D scene from a comprehensive understanding of 3D information, physical radiance field, and varying camera settings inherent in 2D low dynamic range (LDR) images

[Workshop] CVPRw 2023 (3DMV: Learning 3D with Multi-View Supervision)

Proposed a communication-efficient re-parameterization in the federated learning setting