Evaluation of Continuous Image Features Learned by ODE Nets

  title={Evaluation of Continuous Image Features Learned by ODE Nets},
  author={Fabio Carrara and Giuseppe Amato and F. Falchi and Claudio Gennaro},
  booktitle={International Conference on Image Analysis and Processing},
Deep-learning approaches in data-driven modeling relies on learning a finite number of transformations (and representations) of the data that are structured in a hierarchy and are often instantiated as deep neural networks (and their internal activations). State-of-the-art models for visual data usually implement deep residual learning: the network learns to predict a finite number of discrete updates that are applied to the internal network state to enrich it. Pushing the residual learning… 

Continuous ODE-defined Image Features for Adaptive Retrieval

This work experiments with the recently proposed continuous neural networks defined by parametric ordinary differential equations, dubbed ODE-Nets, for adaptive extraction of image representations to approximate the exact feature extraction by taking a previous "near-in-time" hidden state as features with a reduced computational cost.



Stable Architectures for Deep Neural Networks

This paper relates the exploding and vanishing gradient phenomenon to the stability of the discrete ODE and presents several strategies for stabilizing deep learning for very deep networks.

Neural Ordinary Differential Equations

This work shows how to scalably backpropagate through any ODE solver, without access to its internal operations, which allows end-to-end training of ODEs within larger models.

Reversible Architectures for Arbitrarily Deep Residual Neural Networks

From this interpretation, a theoretical framework on stability and reversibility of deep neural networks is developed, and three reversible neural network architectures that can go arbitrarily deep in theory are derived.

Deep Neural Networks Motivated by Partial Differential Equations

A new PDE interpretation of a class of deep convolutional neural networks (CNN) that are commonly used to learn from speech, image, and video data is established and three new ResNet architectures are derived that fall into two new classes: parabolic and hyperbolic CNNs.

Identity Mappings in Deep Residual Networks

The propagation formulations behind the residual building blocks suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation.

Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations

It is shown that many effective networks, such as ResNet, PolyNet, FractalNet and RevNet, can be interpreted as different numerical discretizations of differential equations and established a connection between stochastic control and noise injection in the training process which helps to improve generalization of the networks.

Convolutional Networks with Adaptive Inference Graphs

This work proposes convolutional networks with adaptive inference graphs (ConvNet-AIG) that adaptively define their network topology conditioned on the input image, and observes that ConvNet- AIG shows a higher robustness than ResNets, complementing other known defense mechanisms.

End-to-End Learning of Deep Visual Representations for Image Retrieval

This article uses a large-scale but noisy landmark dataset and develops an automatic cleaning method that produces a suitable training set for deep retrieval, and builds on the recent R-MAC descriptor, which can be interpreted as a deep and differentiable architecture, and presents improvements to enhance it.

From generic to specific deep representations for visual recognition

This paper thoroughly investigates the transferability of ConvNet representations w.r.t. several factors, and shows that different visual recognition tasks can be categorically ordered based on their distance from the source task.

Multi-level Residual Networks from Dynamical Systems View

This paper adopts the dynamical systems point of view, and analyzes the lesioning properties of ResNet both theoretically and experimentally, and proposes a novel method for accelerating ResNet training.