most citedFeature Separation and Recalibration for Adversarial Robustness

2 citations · 4 across the 5 of their papers we have counts for

collaborators

5 papers

eess.AS20231 cited

Deep Video Inpainting Guided by Audio-Visual Self-Supervision

Kyuyeon Kim, Junsik Jung, Woo Jae Kim +1

Humans can easily imagine a scene from auditory information based on their prior knowledge of audio-visual events. In this paper, we mimic this innate human ability in deep learnin…

cs.CV2023

Towards Content-based Pixel Retrieval in Revisited Oxford and Paris

Guoyuan An, Woo Jae Kim, Saelyne Yang +3

This paper introduces the first two pixel retrieval benchmarks. Pixel retrieval is segmented instance retrieval. Like semantic segmentation extends classification to the pixel leve…

cs.GR20231 cited

Pixel-wise Guidance for Utilizing Auxiliary Features in Monte Carlo Denoising

Kyu Beom Han, Olivia G. Odenthal, Woo Jae Kim +1

Auxiliary features such as geometric buffers (G-buffers) and path descriptors (P-buffers) have been shown to significantly improve Monte Carlo (MC) denoising. However, recent appro…

cs.CV20232 cited

Feature Separation and Recalibration for Adversarial Robustness

Woo Jae Kim, Yoonki Cho, Junsik Jung +1

Deep neural networks are susceptible to adversarial attacks due to the accumulation of perturbations in the feature level, and numerous works have boosted model robustness by deact…

cs.CV2022

Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks

Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attenti…