In this paper, we introduce Generative Scene Networks (GSN), which learns to decompose scenes into a collection of many local radiance fields that can be rendered from a free moving camera.
Ranked #1 on Scene Generation on VizDoom
We further show that GIST and RIST can be combined with existing semi-supervised learning methods to boost performance.
By refining the empirical data distribution before training, we redirect model capacity towards high-density regions, which ultimately improves sample fidelity, lowers model capacity requirements, and significantly reduces training time.
Ranked #1 on Conditional Image Generation on ImageNet64x64
Additionally, our proposed fast moving proxies also addresses small gradient issue of proxies, and this component synergizes well with low temperature scaling and Global Max Pooling.
Ranked #2 on Image Retrieval on CARS196
The paper analyzes the accuracy of publicly available object-recognition systems on a geographically diverse dataset.
Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong.
Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
Ranked #3 on Semi-Supervised Image Classification on STL-10
We present a method for skin lesion segmentation for the ISIC 2017 Skin Lesion Segmentation Challenge.
We present a deep learning approach to the ISIC 2017 Skin Lesion Classification Challenge using a multi-scale convolutional neural network.