1k citations · 8k across the 112 of their papers we have counts for
23 papers · 1 filter
AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
Christopher F. Brown, Michal R. Kazmierski, Valerie J. Pasquarella +16
Unprecedented volumes of Earth observation data are continually collected around the world, but high-quality labels remain scarce given the effort required to make physical measure…
Generative models improve fairness of medical classifiers under distribution shifts
Ira Ktena, Olivia Wiles, Isabela Albuquerque +9
A ubiquitous challenge in machine learning is the problem of domain generalisation. This can exacerbate bias against groups or labels that are underrepresented in the datasets used…
Towards Robust Image Classification Using Sequential Attention Models
Daniel Zoran, Mike Chrzanowski, Po-Sen Huang +3
In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception. Specifically, we adversarially train and analyze a ne…
CLEVRER: CoLlision Events for Video REpresentation and Reasoning
Kexin Yi, Chuang Gan, Yunzhu Li +4
The ability to reason about temporal and causal events from videos lies at the core of human intelligence. Most video reasoning benchmarks, however, focus on pattern recognition fr…
A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities
Simon A. A. Kohl, Bernardino Romera-Paredes, Klaus H. Maier-Hein +5
Medical imaging only indirectly measures the molecular identity of the tissue within each voxel, which often produces only ambiguous image evidence for target measures of interest,…
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
Jiayuan Mao, Chuang Gan, Pushmeet Kohli +2
We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; in…
Efficient Relaxations for Dense CRFs with Sparse Higher Order Potentials
Thomas Joy, Alban Desmaison, Thalaiyasingam Ajanthan +5
Dense conditional random fields (CRFs) have become a popular framework for modelling several problems in computer vision such as stereo correspondence and multi-class semantic segm…
Multi-way Particle Swarm Fusion
Chen Liu, Hang Yan, Pushmeet Kohli +1
This paper proposes a novel MAP inference framework for Markov Random Field (MRF) in parallel computing environments. The inference framework, dubbed Swarm Fusion, is a natural gen…
Deep Multi-Modal Image Correspondence Learning
Chen Liu, Jiajun Wu, Pushmeet Kohli +1
Inference of correspondences between images from different modalities is an extremely important perceptual ability that enables humans to understand and recognize cross-modal conce…
Memory-augmented Attention Modelling for Videos
Rasool Fakoor, Abdel-rahman Mohamed, Margaret Mitchell +2
We present a method to improve video description generation by modeling higher-order interactions between video frames and described concepts. By storing past visual attention in t…
Deep disentangled representations for volumetric reconstruction
Edward Grant, Pushmeet Kohli, Marcel van Gerven
We introduce a convolutional neural network for inferring a compact disentangled graphical description of objects from 2D images that can be used for volumetric reconstruction. The…
Efficient Continuous Relaxations for Dense CRF
Alban Desmaison, Rudy Bunel, Pushmeet Kohli +2
Dense conditional random fields (CRF) with Gaussian pairwise potentials have emerged as a popular framework for several computer vision applications such as stereo correspondence a…
Learning to Navigate the Energy Landscape
Julien Valentin, Angela Dai, Matthias Nießner +4
In this paper, we present a novel and efficient architecture for addressing computer vision problems that use `Analysis by Synthesis'. Analysis by synthesis involves the minimizati…
DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding
Yinda Zhang, Mingru Bai, Pushmeet Kohli +2
While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular,…
PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions
Michael Figurnov, Aijan Ibraimova, Dmitry Vetrov +1
We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in low-power devices such a…
Deep Convolutional Inverse Graphics Network
Tejas D. Kulkarni, Will Whitney, Pushmeet Kohli +1
This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a model that learns an interpretable representation of images. This representation is disentangled with…
Memory Bounded Deep Convolutional Networks
Maxwell D. Collins, Pushmeet Kohli
In this work, we investigate the use of sparsity-inducing regularizers during training of Convolution Neural Networks (CNNs). These regularizers encourage that fewer connections in…
Consensus Message Passing for Layered Graphical Models
Varun Jampani, S. M. Ali Eslami, Daniel Tarlow +2
Generative models provide a powerful framework for probabilistic reasoning. However, in many domains their use has been hampered by the practical difficulties of inference. This is…
Inverse Graphics with Probabilistic CAD Models
Tejas D. Kulkarni, Vikash K. Mansinghka, Pushmeet Kohli +1
Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perce…
Multi-utility Learning: Structured-output Learning with Multiple Annotation-specific Loss Functions
Roman Shapovalov, Dmitry Vetrov, Anton Osokin +1
Structured-output learning is a challenging problem; particularly so because of the difficulty in obtaining large datasets of fully labelled instances for training. In this paper w…
Efficient Energy Minimization for Enforcing Statistics
Yongsub Lim, Kyomin Jung, Pushmeet Kohli
Energy minimization algorithms, such as graph cuts, enable the computation of the MAP solution under certain probabilistic models such as Markov random fields. However, for many co…
A two-layer Conditional Random Field for the classification of partially occluded objects
Sergey Kosov, Pushmeet Kohli, Franz Rottensteiner +1
Conditional Random Fields (CRF) are among the most popular techniques for image labelling because of their flexibility in modelling dependencies between the labels and the image fe…
Curvature Prior for MRF-based Segmentation and Shape Inpainting
Alexander Shekhovtsov, Pushmeet Kohli, Carsten Rother
Most image labeling problems such as segmentation and image reconstruction are fundamentally ill-posed and suffer from ambiguities and noise. Higher order image priors encode high…