in Studies on Deep Learning, Computer Vision
Former CNN models fully activate(filly distributed features) for a single input showing poor performance on invariant relational reasoning.
in Studies on Deep Learning, Computer Vision
Hard attention is relatively less explored than soft attention.
Relational information is important in some reinforcement learning tasks.
in Studies on Deep Learning, Deep Learning
Most VQA reasoning algorithms are not transparent in their reasoning and not robust to complex reasoning.
in Studies on Deep Learning, Deep Learning
Constructing 3D shape from a single image is challenging. Training end-to-end to predict 3D shape from 2D image often end up overfitting while not generalizing well to other shapes.
\beta-VAE is known to disentangle latent variables.
in Studies on Deep Learning, Computer Vision
Relational Network showed great performance in relational reasoning, but calculations and memory consumption grow quadratically with the number of the objects due to fully connected pairing process.
Vector offset method is used for word analogy task.
Rejoice in what you learn and spray it!