14.1k citations · 34.6k across the 53 of their papers we have counts for
15 papers · 1 filter
Testing GLOM's ability to infer wholes from ambiguous parts
Laura Culp, Sara Sabour, Geoffrey E. Hinton
The GLOM architecture proposed by Hinton [2021] is a recurrent neural network for parsing an image into a hierarchy of wholes and parts. When a part is ambiguous, GLOM assumes that…
A Generalist Framework for Panoptic Segmentation of Images and Videos
Ting Chen, Lala Li, Saurabh Saxena +2
Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image. As permutations of instance IDs are also valid solutions, the task requires learning of hi…
Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
Ting Chen, Ruixiang Zhang, Geoffrey Hinton
We present Bit Diffusion: a simple and generic approach for generating discrete data with continuous state and continuous time diffusion models. The main idea behind our approach i…
A Unified Sequence Interface for Vision Tasks
Ting Chen, Saurabh Saxena, Lala Li +3
While language tasks are naturally expressed in a single, unified, modeling framework, i.e., generating sequences of tokens, this has not been the case in computer vision. As a res…
Robust and Efficient Medical Imaging with Self-Supervision
Shekoofeh Azizi, Laura Culp, Jan Freyberg +31
Recent progress in Medical Artificial Intelligence (AI) has delivered systems that can reach clinical expert level performance. However, such systems tend to demonstrate sub-optima…
Pix2seq: A Language Modeling Framework for Object Detection
Ting Chen, Saurabh Saxena, Lala Li +2
We present Pix2Seq, a simple and generic framework for object detection. Unlike existing approaches that explicitly integrate prior knowledge about the task, we cast object detecti…
How to represent part-whole hierarchies in a neural network
Geoffrey Hinton
This paper does not describe a working system. Instead, it presents a single idea about representation which allows advances made by several different groups to be combined into an…
Canonical Capsules: Self-Supervised Capsules in Canonical Pose
Weiwei Sun, Andrea Tagliasacchi, Boyang Deng +4
We propose a self-supervised capsule architecture for 3D point clouds. We compute capsule decompositions of objects through permutation-equivariant attention, and self-supervise th…
Unsupervised part representation by Flow Capsules
Sara Sabour, Andrea Tagliasacchi, Soroosh Yazdani +2
Capsule networks aim to parse images into a hierarchy of objects, parts and relations. While promising, they remain limited by an inability to learn effective low level part descri…
NASA: Neural Articulated Shape Approximation
Boyang Deng, JP Lewis, Timothy Jeruzalski +4
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics. To efficiently simulate deformation, existing approach…
CvxNet: Learnable Convex Decomposition
Boyang Deng, Kyle Genova, Soroosh Yazdani +3
Any solid object can be decomposed into a collection of convex polytopes (in short, convexes). When a small number of convexes are used, such a decomposition can be thought of as a…
Cerberus: A Multi-headed Derenderer
Boyang Deng, Simon Kornblith, Geoffrey Hinton
To generalize to novel visual scenes with new viewpoints and new object poses, a visual system needs representations of the shapes of the parts of an object that are invariant to c…
Dynamic Routing Between Capsules
Sara Sabour, Nicholas Frosst, Geoffrey E Hinton
A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part. We use the length of…
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
S. M. Ali Eslami, Nicolas Heess, Theophane Weber +4
We present a framework for efficient inference in structured image models that explicitly reason about objects. We achieve this by performing probabilistic inference using a recurr…
Deep Lambertian Networks
Yichuan Tang, Ruslan Salakhutdinov, Geoffrey Hinton
Visual perception is a challenging problem in part due to illumination variations. A possible solution is to first estimate an illumination invariant representation before using it…