Search Results for author: Esther Robb

Found 3 papers, 3 papers with code

DropLoss for Long-Tail Instance Segmentation

1 code implementation13 Apr 2021 Ting-I Hsieh, Esther Robb, Hwann-Tzong Chen, Jia-Bin Huang

Based on this insight, we develop DropLoss -- a novel adaptive loss to compensate for this imbalance without a trade-off between rare and frequent categories.

Instance Segmentation object-detection +3

Few-Shot Adaptation of Generative Adversarial Networks

1 code implementation22 Oct 2020 Esther Robb, Wen-Sheng Chu, Abhishek Kumar, Jia-Bin Huang

We validate our method in a challenging few-shot setting of 5-100 images in the target domain.

Image Generation

NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

1 code implementation ECCV 2020 Yun-Chun Chen, Chen Gao, Esther Robb, Jia-Bin Huang

Recent work has shown that the structure of deep convolutional neural networks can be used as a structured image prior for solving various inverse image restoration tasks.

Image Restoration Image-to-Image Translation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.