-
Straight to Shapes++: Real-time Instance Segmentation Made More Accurate
Instance segmentation is an important problem in computer vision, with a...
05/27/2019 ∙ by Laurynas Miksys, et al. ∙
0
∙
share
read it
-
With Friends Like These, Who Needs Adversaries?
The vulnerability of deep image classification networks to adversarial a...
07/11/2018 ∙ by Saumya Jetley, et al. ∙
0
∙
share
read it
-
Learn To Pay Attention
We propose an end-to-end-trainable attention module for convolutional ne...
04/06/2018 ∙ by Saumya Jetley, et al. ∙
0
∙
share
read it
-
End-to-End Saliency Mapping via Probability Distribution Prediction
Most saliency estimation methods aim to explicitly model low-level consp...
04/05/2018 ∙ by Saumya Jetley, et al. ∙
2
∙
share
read it
-
Straight to Shapes: Real-time Detection of Encoded Shapes
Current object detection approaches predict bounding boxes, but these pr...
11/23/2016 ∙ by Saumya Jetley, et al. ∙
0
∙
share
read it
-
Prototypical Priors: From Improving Classification to Zero-Shot Learning
Recent works on zero-shot learning make use of side information such as ...
12/03/2015 ∙ by Saumya Jetley, et al. ∙
0
∙
share
read it
