Temporal Action Localization with Variance-Aware Networks

• URL: http://arxiv.org/abs/2008.11254v1
• Date: Tue, 25 Aug 2020 20:12:59 GMT
• Title: Temporal Action Localization with Variance-Aware Networks
• Authors: Ting-Ting Xie, Christos Tzelepis, Ioannis Patras
• Abstract summary: This work addresses the problem of temporal action localization with Variance-Aware Networks (VAN) VANp is a network that propagates the mean and the variance throughout the network to deliver outputs with second order statistics. Results show that VANp surpasses the accuracy of virtually all other two-stage networks without involving any additional parameters.
• Score: 12.364819165688628
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work addresses the problem of temporal action localization with Variance-Aware Networks (VAN), i.e., DNNs that use second-order statistics in the input and/or the output of regression tasks. We first propose a network (VANp) that when presented with the second-order statistics of the input, i.e., each sample has a mean and a variance, it propagates the mean and the variance throughout the network to deliver outputs with second order statistics. In this framework, both the input and the output could be interpreted as Gaussians. To do so, we derive differentiable analytic solutions, or reasonable approximations, to propagate across commonly used NN layers. To train the network, we define a differentiable loss based on the KL-divergence between the predicted Gaussian and a Gaussian around the ground truth action borders, and use standard back-propagation. Importantly, the variances propagation in VANp does not require any additional parameters, and during testing, does not require any additional computations either. In action localization, the means and the variances of the input are computed at pooling operations, that are typically used to bring arbitrarily long videos to a vector with fixed dimensions. Second, we propose two alternative formulations that augment the first (respectively, the last) layer of a regression network with additional parameters so as to take in the input (respectively, predict in the output) both means and variances. Results in the action localization problem show that the incorporation of second order statistics improves over the baseline network, and that VANp surpasses the accuracy of virtually all other two-stage networks without involving any additional parameters.

Related papers

• Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation [58.19676004192321]
  Diffusion models (DMs), which enable both image generation from noise and inversion from data, have inspired powerful unpaired image-to-image (I2I) translation algorithms. We tackle this problem with Schrodinger Bridges (SBs), which are differential equations (SDEs) between distributions with minimal transport cost. Inspired by this observation, we propose Latent Schrodinger Bridges (LSBs) that approximate the SB ODE via pre-trained Stable Diffusion. We demonstrate that our algorithm successfully conduct competitive I2I translation in unsupervised setting with only a fraction of cost required by previous DM-
  arXiv  Detail & Related papers  (2024-11-22T11:24:14Z)
• Flexible Heteroscedastic Count Regression with Deep Double Poisson Networks [4.58556584533865]
  We propose the Deep Double Poisson Network (DDPN) to produce accurate, input-conditional uncertainty representations. DDPN vastly outperforms existing discrete models. It can be applied to a variety of count regression datasets.
  arXiv  Detail & Related papers  (2024-06-13T16:02:03Z)
• Sparsifying Bayesian neural networks with latent binary variables and normalizing flows [10.865434331546126]
  We will consider two extensions to the latent binary Bayesian neural networks (LBBNN) method. Firstly, by using the local reparametrization trick (LRT) to sample the hidden units directly, we get a more computationally efficient algorithm. More importantly, by using normalizing flows on the variational posterior distribution of the LBBNN parameters, the network learns a more flexible variational posterior distribution than the mean field Gaussian.
  arXiv  Detail & Related papers  (2023-05-05T09:40:28Z)
• Optimal Training of Mean Variance Estimation Neural Networks [1.4610038284393165]
  This paper focusses on the optimal implementation of a Mean Variance Estimation network (MVE network) (Nix and Weigend, 1994) An MVE network assumes that the data is produced from a normal distribution with a mean function and variance function. We introduce a novel improvement of the MVE network: separate regularization of the mean and the variance estimate.
  arXiv  Detail & Related papers  (2023-02-17T13:44:47Z)
• Generative Adversarial Networks to infer velocity components in rotating turbulent flows [2.0873604996221946]
  We show that CNN and GAN always outperform EPOD both concerning point-wise and statistical reconstructions. The analysis is performed using both standard validation tools based on $L$ spatial distance between the prediction and the ground truth.
  arXiv  Detail & Related papers  (2023-01-18T13:59:01Z)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• Robust Estimation for Nonparametric Families via Generative Adversarial Networks [92.64483100338724]
  We provide a framework for designing Generative Adversarial Networks (GANs) to solve high dimensional robust statistics problems. Our work extend these to robust mean estimation, second moment estimation, and robust linear regression. In terms of techniques, our proposed GAN losses can be viewed as a smoothed and generalized Kolmogorov-Smirnov distance.
  arXiv  Detail & Related papers  (2022-02-02T20:11:33Z)
• Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks [83.58049517083138]
  We consider a two-layer ReLU network trained via gradient descent. We show that SGD is biased towards a simple solution. We also provide empirical evidence that knots at locations distinct from the data points might occur.
  arXiv  Detail & Related papers  (2021-11-03T15:14:20Z)
• Predicting Deep Neural Network Generalization with Perturbation Response Curves [58.8755389068888]
  We propose a new framework for evaluating the generalization capabilities of trained networks. Specifically, we introduce two new measures for accurately predicting generalization gaps. We attain better predictive scores than the current state-of-the-art measures on a majority of tasks in the Predicting Generalization in Deep Learning (PGDL) NeurIPS 2020 competition.
  arXiv  Detail & Related papers  (2021-06-09T01:37:36Z)
• Empirical Strategy for Stretching Probability Distribution in Neural-network-based Regression [5.35308390309106]
  In regression analysis under artificial neural networks, the prediction performance depends on determining the appropriate weights between layers. We proposed weighted empirical stretching (WES) as a novel loss function to increase the overlap area of the two distributions. The improved results in RMSE for the extreme domain are expected to be utilized for prediction of abnormal events in non-linear complex systems.
  arXiv  Detail & Related papers  (2020-09-08T06:08:14Z)
• Network Moments: Extensions and Sparse-Smooth Attacks [59.24080620535988]
  We derive exact analytic expressions for the first and second moments of a small piecewise linear (PL) network (Affine, ReLU, Affine) subject to Gaussian input. We show that the new variance expression can be efficiently approximated leading to much tighter variance estimates.
  arXiv  Detail & Related papers  (2020-06-21T11:36:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.