Italy

The deep learning models, which include attention mechanisms, are shown to enhance the performance and efficiency of the various computer vision tasks such as pattern recognition, object detection, face recognition, etc. Although the visual attention mechanism is the source of inspiration for these models, recent attention models consider `attention&#39; as a pure machine vision optimization problem, and visual attention remains the most neglected aspect. Therefore, this paper presents a collaborative human and machine attention module which considers both visual and network&#39;s attention. The proposed module is inspired by the dorsal (`where&#39;) pathways of visual processing and can be integrated with any convolutional neural network (CNN) model. First, the module computes the spatial attention map from the input feature maps, which is then combined with the visual attention maps. The visual attention maps are created using eye-fixations obtained by performing an eye-tracking experiment with human participants. The visual attention map covers the highly salient and discriminating image regions as humans tend to focus on such regions, whereas the other relevant image regions are processed by spatial attention map. The combination of these two maps results in finer refinement in feature maps, resulting in improved performance. The comparative analysis reveals that our model not only shows significant improvement over the baseline model but also outperforms the other models. We hope that our findings using a collaborative human-machine attention module will be helpful in other computer vision tasks as well.

ICPR 2020

Collaborative Human Machine Attention Module
for Character Recognition

attention mechanism

eye-tracking

human-machine collaboration

deep neural networks

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. 


The deep learning models, which include attention mechanisms, are shown to enhance the performance and efficiency of the various computer vision tasks such as pattern recognition, object detection, face recognition, etc. Although the visual attention mechanism is the source of inspiration for these models, recent attention models consider `attention' as a pure machine vision optimization problem, and visual attention remains the most neglected aspect. Therefore, this paper presents a collaborative human and machine attention module which considers both visual and network's attention. The proposed module is inspired by the dorsal (`where') pathways of visual processing and can be integrated with any convolutional neural network (CNN) model. First, the module computes the spatial attention map from the input feature maps, which is then combined with the visual attention maps. The visual attention maps are created using eye-fixations obtained by performing an eye-tracking experiment with human participants. The visual attention map covers the highly salient and discriminating image regions as humans tend to focus on such regions, whereas the other relevant image regions are processed by spatial attention map. The combination of these two maps results in finer refinement in feature maps, resulting in improved performance. The comparative analysis reveals that our model not only shows significant improvement over the baseline model but also outperforms the other models. We hope that our findings using a collaborative human-machine attention module will be helpful in other computer vision tasks as well.

poster

Given the overwhelming impact of machine learning on the last decade, several libraries and frameworks have been developed in recent years to simplify the design and training of neural networks, providing array-based programming, automatic differentiation and user-friendly access to hardware accelerators. None of those tools, however, was designed with native and transparent support for Cloud Computing or heterogeneous High-Performance Computing (HPC). The DeepHealth Toolkit is an open source Deep Learning toolkit aimed at boosting productivity of data scientists operating in the medical field by
providing a unified framework for the distributed training of neural networks, which is able to leverage hybrid HPC and cloud environments in a transparent way for the user. The toolkit is composed of a Computer Vision library, a Deep Learning library, and a front-end for non-expert users; all of the components are focused on the medical domain, but they are general purpose and can be applied to any other field. In this paper, the principles driving the design of the DeepHealth libraries are described, along with details about the implementation and the interaction between the different elements composing the toolkit. Finally, experiments on common benchmarks prove the efficiency of each separate component and of the DeepHealth Toolkit overall.

The DeepHealth Toolkit: A Unified Framework to Boost Biomedical Applications

Automatic detection for threat object items is an increasing emerging area of future application in X-ray security imagery. Although modern X-ray security scanners can provide two or more views, the integration of such object detectors across the views has not been widely explored with rigour. Therefore, we investigate the application of geometric constraints using the epipolar nature of multi-view imagery to improve object detection performance. Furthermore, we assume that images come from uncalibrated views, such that a method to estimate the fundamental matrix using ground truth bounding box centroids from multiple view object labels is proposed. In addition, detections are given a confidence probability based on its similarity with respect to the distribution of the distance to the epipolar line. This probability is used as confidence weights for merging duplicated predictions using non-maximum suppression. Using a standard object detector (YOLOv3), our technique increases the average precision of detection by 2.8% on a dataset composed of firearms, laptops, knives and cameras. These results indicate that the integration of images at different views significantly improves the detection performance of threat items of cluttered X-ray security images.

Multi-view Object Detection Using Epipolar Constraints within Cluttered X-ray Security Imagery

Quantized low-precision neural networks are very popular because they require less computational resources for inference and can provide high performance, which is vital for real-time and embedded recognition systems. However, their advantages are apparent for FPGA and ASIC devices, while general-purpose processor architectures are not always able to perform low-bit integer computations efficiently. 
The most frequently used low-precision neural network model for mobile central processors is an 8-bit quantized network. However, in a number of cases, it is possible to use fewer bits for weights and activations, and the only problem is the difficulty of efficient implementation.
We introduce an efficient implementation of 4-bit matrix multiplication for quantized neural networks and perform time measurements on a mobile ARM processor. It shows 2.9 times speedup compared to standard floating-point multiplication and is 1.5 times faster than 8-bit quantized one. We also demonstrate a 4-bit quantized neural network for OCR recognition on the MIDV-500 dataset. 4-bit quantization gives 95.0% accuracy and 48% overall inference speedup, while an 8-bit quantized network gives 95.4% accuracy and 39% speedup. The results show that 4-bit quantization perfectly suits mobile devices, yielding good enough accuracy and low inference time.

Fast Implementation of 4-bit Convolutional Neural Networks for Mobile Devices


This paper studies the problem of Person Re-Identification (ReID)
for large-scale applications. Recent research efforts have been devoted
to building complicated part models, which introduce considerably
high computational cost and memory consumption, inhibiting its practicability
in large-scale applications. This paper aims to develop a novel learning
strategy to find efficient feature embeddings while maintaining the
balance of accuracy and model complexity. More specifically, we find
by enhancing the classical triplet loss together with cross-entropy
loss, our method can explore the hard examples and build a discriminant
feature embedding yet compact enough for large-scale applications.
Our method is carried out progressively using Bayesian optimization,
and we call it the Progressive Learning Algorithm (PLA). Extensive
experiments on three large-scale datasets show that our PLA is comparable
or better than the state-of-the-arts. Especially, on the challenging
Market-1501 dataset, we achieve Rank-1=94.7%/mAP=89.4% while saving
at least 30\% parameters than strong part models.

Deep Transfer Learning for Alzheimer's disease detection

Audio-Visual Predictive Coding for Self-Supervised Visual Representation Learning

Active learning aims to optimize the dataset annotation process when resources are constrained.
Most existing methods are designed for balanced datasets.
Their practical applicability is limited by the fact that a majority of real-life datasets are actually imbalanced.
Here, we introduce a new active learning method which is designed for imbalanced datasets.
It favors samples likely to be in minority classes so as to reduce the imbalance of the labeled subset and create a better representation for these classes. 
We also compare two training schemes for active learning: (1) the one commonly deployed in deep active learning using model fine tuning for each iteration and (2) a scheme which is inspired by transfer learning and exploits generic pre-trained models and train shallow classifiers for each iteration.
Evaluation is run with three imbalanced datasets.
Results show that the proposed active learning method outperforms competitive baselines.
Equally interesting, they also indicate that the transfer learning training scheme outperforms model fine tuning if features are transferable from the generic dataset to the unlabeled one. 
This last result is surprising and should encourage the community to explore the design of deep active learning methods.

Minority Class Oriented Active Learning for Imbalanced Datasets

Deploying deep learning models with millions, even billions, of parameters is challenging given real world memory, power and compute constraints. In an effort to make these models more practical, in this paper, we propose a novel model compression approach that exploits linear dependence between the activations in a layer to eliminate entire structural units (neurons/convolutional filters). Our approach also adjusts the weights of the layer in a manner that is provably lossless while training if the removed neuron was perfectly predictable. We combine this approach with an annealing algorithm that may be applied during training, or even on a trained model, and demonstrate, using popular datasets, that our technique can reduce the parameters of VGG and AlexNet by more than 97% on CIFAR-10, 85% on Caltech-256, and 19% on ImageNet at less than 2% loss in accuracy. Furthermore, we provide theoretical results showing that in overparametrized, locally linear (ReLU) neural networks where redundant features exist, and with
correct hyperparameter selection, our method is indeed able to capture
and suppress those dependencies.


Exploiting Non-Linear Redundancy for Neural Model Compression

Recently, many multi-stream gaze estimation methods have been proposed. They estimate gaze from eye and face appearances and achieve reasonable accuracy. However, most of the methods simply concatenate the features extracted from eye and face appearance. The feature fusion process has been ignored. Thus, we propose a novel Adaptive Feature Fusion Network (AFF-Net), which performs gaze tracking task in mobile tablets. We stack two-eye feature maps and utilize Squeeze-and-Excitation layers to adaptively fuse two-eye features according to their similarity on appearance. Meanwhile, we also propose Adaptive Group Normalization to recalibrate eye features with the guidance of facial feature. Extensive experiments on both GazeCapture and MPIIFaceGaze datasets demonstrate consistently superior performance of the proposed method.


Adaptive Feature Fusion Network for Gaze Tracking in Mobile Tablets

Topological Data Analysis (TDA) is a rising field in machine learning. TDA seeks to extract information about the shape of a data set by examining its topological and geometric properties. Persistence diagrams, one of main tools in TDA, store topological information about the data. Persistence curves, a recently developed framework, provides a canonical and flexible way to encode the information presented in persistence diagrams into vectors. Based on persistence curves, the main contributions of this work are to (1) provide new sets of features for time series (2) propose a hybrid metric that takes both geometric and topological information of the time series into account, and (3) we apply these metrics to all the datasets in the UCR Time Series Classification Archive. Empirical results show that the proposed metrics perform better than the relevant benchmark in most cases.

A Hybrid Metric Based on Persistent Homology and Its Application to Signal Classification

In this work, we propose a novel method to generate compact image representations which uses local spatial information through an attention mechanism, named Generalized Local Attention Pooling (GLAP). This method, instead of being placed at the end layer of the backbone, is connected at an intermediate level, resulting in lower memory requirements. 
Experiments showcase that our proposed mechanism outperforms other pooling methods when compared with current state-of-the-art losses for deep metric learning.

Downloads

Next from ICPR 2020

The DeepHealth Toolkit: A Unified Framework to Boost Biomedical Applications

Similar lecture

Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?