-
An Investigation on Different Underlying Quantization Schemes for Pre-trained Language Models
Recently, pre-trained language models like BERT have shown promising per...
10/14/2020 ∙ by Zihan Zhao, et al. ∙
3
∙
share
read it
-
From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation
Zero-shot learning has been actively studied for image classification ta...
09/25/2020 ∙ by Zhangxuan Gu, et al. ∙
10
∙
share
read it
-
Context-aware Feature Generation for Zero-shot Semantic Segmentation
Existing semantic segmentation models heavily rely on dense pixel-wise a...
08/16/2020 ∙ by Zhangxuan Gu, et al. ∙
0
∙
share
read it
