no code implementations • 12 Apr 2022 • Zhaowei Cai, Gukyeong Kwon, Avinash Ravichandran, Erhan Bas, Zhuowen Tu, Rahul Bhotika, Stefano Soatto
In this paper, we study the challenging instance-wise vision-language tasks, where the free-form language is required to align with the objects instead of the whole image.
1 code implementation • 8 Mar 2022 • Gukyeong Kwon, Ghassan AlRegib
Also, the two-stream autoencoder works as a unified framework for the gating model and the unseen expert, which makes the proposed method computationally efficient.
no code implementations • 13 Aug 2020 • Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
To articulate the significance of the model perspective in novelty detection, we utilize backpropagated gradients.
2 code implementations • 1 Aug 2020 • Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib
Current modes of visual explanations answer questions of the form $`Why \text{ } P?'$.
2 code implementations • ECCV 2020 • Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
Anomalies require more drastic model updates to fully represent them compared to normal data.
no code implementations • ICLR 2020 • Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
To complement the learned information from activation-based representation, we propose utilizing a gradient-based representation that explicitly focuses on missing information.
no code implementations • 25 Sep 2019 • Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib
Such a positioning scheme is based on a data point’s second-order property.
2 code implementations • 27 Aug 2019 • Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib
In this paper, we utilize weight gradients from backpropagation to characterize the representation space learned by deep learning algorithms.
no code implementations • 17 Feb 2019 • Mohit Prabhushankar, Gukyeong Kwon, Dogancan Temel, Ghassan AlRegib
In this paper, we generate and control semantically interpretable filters that are directly learned from natural images in an unsupervised fashion.
2 code implementations • 12 Dec 2018 • Mohammed A. Aabed, Gukyeong Kwon, Ghassan AlRegib
This is a full-reference tempospatial approach that considers both temporal and spatial PSD characteristics.
1 code implementation • 7 Dec 2017 • Dogancan Temel, Gukyeong Kwon, Mohit Prabhushankar, Ghassan AlRegib
We benchmark the performance of existing solutions in real-world scenarios and analyze the performance variation with respect to challenging conditions.