Search Results for author:
Found 25 papers, 9 papers with code
Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set
We introduce a video compression algorithm based on instance-adaptive learning.
Skip-Convolutions for Efficient Video Processing
We reformulate standard convolution to be efficiently computed on residual frames: each layer is coupled with a binary gate deciding whether a residual is important to the model prediction,~\eg foreground regions, or it can be safely skipped, e. g. background regions.
A Combined Deep Learning based End-to-End Video Coding Architecture for YUV Color Space
Most of the existing deep learning based end-to-end video coding (DLEC) architectures are designed specifically for RGB color format, yet the video coding standards, including H. 264/AVC, H. 265/HEVC and H. 266/VVC developed over past few decades, have been designed primarily for YUV 4:2:0 format, where the chrominance (U and V) components are subsampled to achieve superior compression performances considering the human visual system.
Transform Network Architectures for Deep Learning based End-to-End Image/Video Coding in Subsampled Color Spaces
Most of the existing deep learning based end-to-end image/video coding (DLEC) architectures are designed for non-subsampled RGB color format.
Overfitting for Fun and Profit: Instance-Adaptive Data Compression
At a high level, neural compression is based on an autoencoder that tries to reconstruct the input instance from a (quantized) latent representation, coupled with a prior that is used to losslessly compress these latents.
Lossy Compression with Distortion Constrained Optimization
We argue that the constrained optimization method of Rezende and Viola, 2018 is a lot more appropriate for training lossy compression models because it allows us to obtain the best possible rate subject to a distortion constraint.
A Data and Compute Efficient Design for Limited-Resources Deep Learning
Thanks to their improved data efficiency, equivariant neural networks have gained increased interest in the deep learning community.
Feedback Recurrent Autoencoder for Video Compression
Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems.
Learning Discrete Distributions by Dequantization
Media is generally stored digitally and is therefore discrete.
Feedback Recurrent AutoEncoder
In this work, we propose a new recurrent autoencoder architecture, termed Feedback Recurrent AutoEncoder (FRAE), for online compression of sequential data with temporal dependency.
Video Compression With Rate-Distortion Autoencoders
We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding.
Covariance in Physics and Convolutional Neural Networks
In this proceeding we give an overview of the idea of covariance (or equivariance) featured in the recent development of convolutional neural networks (CNNs).
Gauge Equivariant Convolutional Networks and the Icosahedral CNN
The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design.
Ranked #23 on
Semantic Segmentation
on Stanford2D3D Panoramic
Explorations in Homeomorphic Variational Auto-Encoding
Our experiments show that choosing manifold-valued latent variables that match the topology of the latent data manifold, is crucial to preserve the topological structure and learn a well-behaved latent space.
Sample Efficient Semantic Segmentation using Rotation Equivariant Convolutional Networks
The group equivariant CNN framework is extended for segmentation by introducing a new equivariant (G->Z2)-convolution that transforms feature maps on a group to planar feature maps.
3D G-CNNs for Pulmonary Nodule Detection
Convolutional Neural Networks (CNNs) require a large amount of annotated data to learn from, which is often difficult to obtain in the medical domain.
Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)
In algebraic terms, the feature spaces in regular G-CNNs transform according to a regular representation of the group G, whereas the feature spaces in Steerable G-CNNs transform according to the more general induced representations of G. In order to make the network equivariant, each layer in a G-CNN is required to intertwine between the induced representations associated with its input and output space.
HexaConv
We find that, due to the reduced anisotropy of hexagonal filters, planar HexaConv provides better accuracy than planar convolution with square filters, given a fixed parameter budget.
Spherical CNNs
Convolutional Neural Networks (CNNs) have become the method of choice for learning problems involving 2D planar images.
Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
This article presents the prediction difference analysis method for visualizing the response of a deep neural network to a specific input.
Steerable CNNs
It has long been recognized that the invariance and equivariance properties of a representation are critically important for success in many vision tasks.
A New Method to Visualize Deep Neural Networks
We present a method for visualising the response of a deep neural network to a specific input.
Group Equivariant Convolutional Networks
We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries.
Ranked #6 on
Breast Tumour Classification
on PCam
Breast Tumour Classification
Colorectal Gland Segmentation:
+2
Harmonic Exponential Families on Manifolds
In a range of fields including the geosciences, molecular biology, robotics and computer vision, one encounters problems that involve random variables on manifolds.
Transformation Properties of Learned Visual Representations
Starting with the idea that a good visual representation is one that transforms linearly under scene motions, we show, using the theory of group representations, that any such representation is equivalent to a combination of the elementary irreducible representations.
