Italy

In this paper, we propose a novel network training mechanism called ”dynamic channel propagation” to prune the neural networks during the training period. In particular, we pick up a specific group of channels in each convolutional layer to participate in the forward propagation in training time according to the significance level of channel, which is defined as channel utility. The utility values with respect to all selected channels are updated simultaneously with the error back-propagation process and will adaptively change. Furthermore, when the training ends, channels with high utility values are retained whereas those with low utility values are discarded. Hence, our proposed scheme trains and prunes neural networks simultaneously. We empirically evaluate our novel training scheme on various representative benchmark datasets and advanced convolutional neural network (CNN) architectures, including VGGNet and ResNet. The experiment results verify the superior performance and robust effectiveness of our approach.

ICPR 2020

Learning to Prune in Training via Dynamic Channel Propagation

dynamic channel propagation

channel pruning

deep learning compression

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


technical paper

An essential yet challenging issue in crowd counting is the diverse background variations under complicated real-life environments, which makes attention based methods favorable in recent years. However, most existing methods only rely on firstorder attention schemes (e.g. 2D position-wise attention), while ignoring the higher-order information within the congested scenes completely. In this paper, we propose a hybrid attention-aware network (HANet) with a high-order attention module (HAM) and an adaptive compensation loss (ACLoss) to tackle this problem. On the one hand, the HAM applies 3D attention to capture the subtle discriminative features around each people in the crowd. On the other hand, with the distributed supervision, the ACLoss exploits the prior knowledge from higher-level stages to guide the density map prediction at a lower level. The proposed HANet is then established with HAM and ACLoss working as different roles and promoting each other. Extensive experimental results show the superiority of our HANet against the state-of-the-arts on three challenging benchmarks.

HANet: Hybrid Attention-aware Network for Crowd Counting

Stochastic gradient descent (SGD) usually samples training data based on the uniform distribution, which may not be a good choice because of the high variance of its stochastic gradient. Thus, importance sampling methods are considered in the literature to improve the performance. Most previous work on SGD-based methods with importance sampling requires the knowledge of Lipschitz constants of all component gradients, which are in general difﬁcult to estimate. In this paper, we study an adaptive importance sampling method for common SGDbased methods by exploiting the local ﬁrst-order information without knowing any Lipschitz constants. In particular, we periodically changes the sampling distribution by only utilizing the gradient norms in the past few iterations. We prove that our adaptive importance sampling non-asymptotically reduces the variance of the stochastic gradients in SGD, and thus better convergence bounds than that for vanilla SGD can be obtained. We extend this sampling method to several other widely used stochastic gradient algorithms including SGD with momentum and ADAM. Experiments on common convex learning problems and deep neural networks illustrate notably enhanced performance using the adaptive sampling strategy.

Low-Cost Lipschitz-Independent Adaptive Importance Sampling of Stochastic Gradients

This paper tackles the problem of human action recognition, defined as classifying which action is displayed in a trimmed sequence, from skeletal data. Albeit state-of-the-art approaches designed for this application are all supervised, in this paper we pursue a more challenging direction: solving the problem with unsupervised learning. To this end, we propose a novel subspace clustering method, which exploits covariance matrix to enhance the action’s discriminability and a timestamp pruning approach that allow us to better handle the temporal dimension of the data. Through a broad experimental validation, we show that our computational pipeline surpasses existing unsupervised approaches but also can result in favorable performances as compared to the supervised methods.

Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning

In one-class novelty detection, a model learns solely on the in-class data to single out out-class instances. Autoencoder (AE) variants aim to compactly model the in-class data to reconstruct it exclusively, thus differentiating the in-class from out-class by the reconstruction error. However, compact modeling in an improper way might collapse the latent representations of the in-class data and thus their reconstruction, which would lead to performance deterioration. Moreover, to properly measure the reconstruction error of high-dimensional data, a metric is required that captures high-level semantics of the data. To this end, we propose Discriminative Compact AE (DCAE) that learns both compact and collapse-free latent representations of the in-class data, thereby reconstructing them both finely and exclusively. In DCAE, (a) we force a compact latent space to bijectively represent the in-class data by reconstructing them through internal discriminative layers of generative adversarial nets. (b) Based on the deep encoder's vulnerability to open set risk, out-class instances are encoded into the same compact latent space and reconstructed poorly without sacrificing the quality of in-class data reconstruction. (c) In inference, the reconstruction error is measured by a novel metric that computes the dissimilarity between a query and its reconstruction based on the class semantics captured by the internal discriminator. Extensive experiments on public image datasets validate the effectiveness of our proposed model on both novelty and adversarial example detection, delivering state-of-the-art performance.

Discriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detection

Feature extraction methods have been successfully applied to many real-world applications. The classical Linear Discriminant Analysis (LDA) and its variants are widely used as feature extraction methods. Although they have been used
for different classification tasks, these methods have some shortcomings.
The main one is that the projection axes obtained are not informative about the relevance of original features. In this paper, we propose a linear embedding method that merges two interesting properties: Robust LDA and inter-class sparsity.
Furthermore, the targeted projection transformation focuses on the most discriminant original features, The proposed method is called Robust Discriminant Analysis with Feature Selection and Inter-class Sparsity (RDA FSIS). Two kinds of sparsity are explicitly included in the proposed model. The first kind is obtained by imposing the `2;1 constraint on the projection matrix in order to perform feature ranking. The second kind is obtained by imposing the inter-class sparsity constraint used for getting a common sparsity structure in each class. Comprehensive experiments on five real-world image datasets demonstrate the effectiveness and advantages of our framework over existing linear methods.

Linear Embedding by Joint Robust Discriminant Analysis and Inter-class Sparsity

A simple but effective deep clustering method.

(Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding

Point cloud processing and 3D shape understanding are
challenging tasks for which deep learning techniques have
demonstrated great potentials. Still further progresses are
essential to allow artificial intelligent agents to
interact with the real world. In many practical conditions
the amount of annotated data may be limited and integrating
new sources of knowledge becomes crucial to support
autonomous learning. Here we consider several scenarios
involving synthetic and real world point clouds where
supervised learning fails due to data scarcity and large
domain gaps. We propose to enrich standard feature
representations by leveraging self-supervision through a
multi-task model that can solve a 3D puzzle while learning
the main task of shape classification or part segmentation.
An extensive analysis investigating few-shot, transfer
learning and cross-domain settings shows the effectiveness
of our approach with state-of-the-art results.

Joint Supervised and Self-Supervised Learning for 3D Real World Challenges

We propose Fast Direction-Search-Based Subspace Clustering (Fast DiSC), a scalable and robust framework for large scale clustering that rests upon representations derived from projections on computed data-dependent directions. To advance scalability, a Direction Search in Data Partitions (DiSPart) procedure performs direction-search in small partitions of sampled data, followed by retrieval using Retrieval using Direction-based Projections (ReDiP) to cluster out-of-sample data using projections on the computed directions and the associated clustering. A theoretical study establishes the correctness of the direction-based clustering framework and that of direction-search in small partitions. In turn, Fast DiSC can provably realize substantial speedups while maintaining high accuracy.

Scalable Direction-Search-Based Approach to Subspace Clustering

Intersection scenarios provide the most complex trafﬁc situations in Autonomous Driving and Driving Assistance Systems. Knowing where to stop in advance in an intersection is an essential parameter in controlling the longitudinal velocity of the vehicle. Most of the existing methods in literature solely use cameras to detect stop lines, which is typically not sufﬁcient in terms of detection range. To address this issue, we propose a method that takes advantage of fused multi-sensory data including stereo camera and lidar as input and utilizes a carefully designed convolutional neural network architecture to detect stop lines. Our experiments show that the proposed approach can improve detection range compared to camera data alone, works under heavy occlusion without observing the ground markings explicitly, is able to predict stop lines for all lanes and allows detection at a distance up to 50 meters.

Holistic Grid Fusion Based Stop Line Estimation

Survival data is often collected in medical applications from a heterogeneous population of patients. While in the past, popular survival models focused on modeling the average effect of the covariates on survival outcomes, rapidly advancing sensing and information technologies have provided opportunities to further model the heterogeneity of the population as well as the non-linearity of the survival risk. With this motivation, we propose a new semi-parametric Bayesian Survival Rule List model in this paper. Our model derives a rule-based decision-making approach, while within the regime defined by each rule, survival risk is modelled via a Gaussian process latent variable model. Markov Chain Monte Carlo with a nested Laplace approximation on the Gaussian process posterior is used to search over the posterior of the rule lists efficiently. The use of ordered rule lists enables us to model heterogeneity while keeping the model complexity in check. Performance evaluations on a synthetic heterogeneous survival dataset and a real world sepsis survival dataset demonstrate the effectiveness of our model.

Premium content

Learning to Prune in Training via Dynamic Channel Propagation

Downloads

Next from ICPR 2020

HANet: Hybrid Attention-aware Network for Crowd Counting

Similar lecture

Learning to Prune in Training via Dynamic Channel Propagation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES