While bilinear model is an effective method for capturing the relationship between two spaces, often the number of parameters is intractable. This paper suggests to reduce the number of parameters by controlling the rank of the matrix with Turker decomposition.
Previous methods for visual question answering performed one-step or static reasoning while some questions requires chain of reasonings.
in Studies on Deep Learning, Computer Vision
Spatial sampling of convolutional neural network is geometrically fixed. This paper suggests two modules for CNN to capture the geometric structure more flexibly.
A caption of an image can be generated with attention based model by aligning a word to a part of image.
in Studies on Deep Learning, Deep Learning
Recent neural network models are getting bigger to increase the performance to the limit. This paper suggests MobileNet to reduce the size of neural network small enough to deploy on mobile devices.
in Studies on Deep Learning, Computer Vision
Image segmentation requires a lot of annotated images. This paper suggests efficient training of image segmentation using data augmentation and new structure.
High quality disentangled generation of images has been the goal for all the generative models. This paper suggests style-based generator architecture for GAN with techniques borrowed from the field of style transfer.
Rejoice in what you learn and spray it!