41 citations · 203 across the 38 of their papers we have counts for
9 papers · 1 filter
Explanation on Pretraining Bias of Finetuned Vision Transformer
Bumjin Park, Jaesik Choi
As the number of fine tuning of pretrained models increased, understanding the bias of pretrained model is essential. However, there is little tool to analyse transformer architect…
Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
Jiyeon Han, Hwanil Choi, Yunjey Choi +3
Evaluation metrics in image synthesis play a key role to measure performances of generative models. However, most metrics mainly focus on image fidelity. Existing diversity metrics…
Can We Find Neurons that Cause Unrealistic Images in Deep Generative Networks?
Hwanil Choi, Wonjoon Chang, Jaesik Choi
Even though Generative Adversarial Networks (GANs) have shown a remarkable ability to generate high-quality images, GANs do not always guarantee the generation of photorealistic im…
An Unsupervised Way to Understand Artifact Generating Internal Units in Generative Neural Networks
Haedong Jeong, Jiyeon Han, Jaesik Choi
Despite significant improvements on the image generation performance of Generative Adversarial Networks (GANs), generations with low visual fidelity still have been observed. As wi…
Automatic Correction of Internal Units in Generative Neural Networks
Ali Tousi, Haedong Jeong, Jiyeon Han +2
Generative Adversarial Networks (GANs) have shown satisfactory performance in synthetic image generation by devising complex network structure and adversarial training scheme. Even…
Interpreting Deep Neural Networks with Relative Sectional Propagation by Analyzing Comparative Gradients and Hostile Activations
Woo-Jeoung Nam, Jaesik Choi, Seong-Whan Lee
The clear transparency of Deep Neural Networks (DNNs) is hampered by complex internal structures and nonlinear transformations along deep hierarchies. In this paper, we propose a n…