We construct an unsupervised learning model that achieves nonlinear disentanglement of underlying factors of variation in naturalistic videos.
Ranked #1 on Disentanglement on Natural Sprites
no code implementations • • Ivan Ustyuzhaninov, Santiago A. Cadena, Emmanouil Froudarakis, Paul G. Fahey, Edgar Y. Walker, Erick Cobos, Jacob Reimer, Fabian H. Sinz, Andreas S. Tolias, Matthias Bethge, Alexander S. Ecker
Similar to a convolutional neural network (CNN), the mammalian retina encodes visual information into several dozen nonlinear feature maps, each formed by one ganglion cell type that tiles the visual space in an approximately shift-equivariant manner.
Learning how to model complex scenes in a modular way with recombinable components is a pre-requisite for higher-order reasoning and acting in the physical world.
Similarly, deep Gaussian processes (DGPs) should allow us to compute a posterior distribution of compositions of multiple functions giving rise to the observations.
We here develop a new set of gradient-based adversarial attacks which (a) are more reliable in the face of gradient-masking than other gradient-based attacks, (b) perform better and are more query efficient than current state-of-the-art gradient-based attacks, (c) can be flexibly adapted to a wide range of adversarial criteria and (d) require virtually no hyperparameter tuning.
We propose a new framework for imposing monotonicity constraints in a Bayesian nonparametric setting based on numerical solutions of stochastic differential equations.
We demonstrate empirical results on MS Coco highlighting challenges of the one-shot setting: while transferring knowledge about instance segmentation to novel object categories works very well, targeting the detection network towards the reference category appears to be more difficult.
Ranked #1 on One-Shot Instance Segmentation on COCO
We present a probabilistic model for unsupervised alignment of high-dimensional time-warped sequences based on the Dirichlet Process Mixture Model (DPMM).
We introduce one-shot texture segmentation: the task of segmenting an input image containing multiple textures given a patch of a reference texture.
The current state of the art in parametric texture synthesis relies on the multi-layer feature space of deep CNNs that were trained on natural images.