Search Results for author:
Found 15 papers, 10 papers with code
RobustNeRF: Ignoring Distractors with Robust Losses
To cope with distractors, we advocate a form of robust estimation for NeRF training, modeling distractors in training data as outliers of an optimization problem.
Testing GLOM's ability to infer wholes from ambiguous parts
The GLOM architecture proposed by Hinton [2021] is a recurrent neural network for parsing an image into a hierarchy of wholes and parts.
nerf2nerf: Pairwise Registration of Neural Radiance Fields
We introduce a technique for pairwise registration of neural fields that extends classical optimization-based local registration (i. e. ICP) to operate on Neural Radiance Fields (NeRF) -- neural 3D scene representations trained from collections of calibrated images.
Kubric: A scalable dataset generator
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.
Conditional Object-Centric Learning from Video
Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built.
Canonical Capsules: Self-Supervised Capsules in Canonical Pose
We propose a self-supervised capsule architecture for 3D point clouds.
Unsupervised part representation by Flow Capsules
Capsule networks aim to parse images into a hierarchy of objects, parts and relations.
Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
Then, we diagnose the adversarial examples for CapsNets and find that the success of the reconstructive attack is highly related to the visual similarity between the source and target class.
Stacked Capsule Autoencoders
In the second stage, SCAE predicts parameters of a few object capsules, which are then used to reconstruct part poses.
Ranked #3 on
Unsupervised MNIST
on MNIST
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models.
DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules
In addition to being trained to classify images, the capsule model is trained to reconstruct the images from the pose parameters and identity of the correct top-level capsule.
Optimal Completion Distillation for Sequence Learning
We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance.
Matrix capsules with EM routing
A capsule in one layer votes for the pose matrix of many different capsules in the layer above by multiplying its own pose matrix by trainable viewpoint-invariant transformation matrices that could learn to represent part-whole relationships.
Ranked #4 on
Image Classification
on smallNORB
Dynamic Routing Between Capsules
We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters.
Ranked #1 on
Image Classification
on MultiMNIST
Adversarial Manipulation of Deep Representations
We show that the representation of an image in a deep neural network (DNN) can be manipulated to mimic those of other natural images, with only minor, imperceptible perturbations to the original image.
