Italy

Eye movements are intricate and dynamic events that contain a wealth of information about the subject and the stimuli. We propose an abstract representation of eye movements that preserve the important nuances in gaze behavior while being stimuli-agnostic. We consider eye movements as raw position and velocity signals and train separate deep temporal convolutional autoencoders. The autoencoders learn micro-scale and macro-scale representations that correspond to the fast and slow features of eye movements. We evaluate the joint representations with a linear classifier fitted on various classification tasks. Our work accurately discriminates between gender and age groups and outperforms previous works on biometrics and stimuli classification. Further experiments highlight the validity and generalizability of this method, bringing eye-tracking research closer to real-world applications.

ICPR 2020

GazeMAE: General Representations of Eye Movements using a Micro-Macro Autoencoder

gaze

autoencoder

eye-tracking

deep learning

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. 


poster

Face Image retrieval is one of the key research directions in computer vision field. Thanks to the rapid development of deep neural network in recent years, deep hashing has achieved good performance in the field of image retrieval. But for largescale face image retrieval, the performance needs to be further improved. In this paper, we propose Deep Face Hashing with GAN (DFH-GAN), a novel deep hashing method for face image retrieval, which mainly consists of three components: a generator network for generating synthesized images, a discriminator network with a shared CNN to learn multi-domain face feature, and a hash encoding network to generate compact binary hash codes. The generator network is used to perform data augmentation so that the model could learn from both real images and diverse synthesized images. We adopt a two-stage training strategy. In the first stage, the GAN is trained to generate fake images, while in the second stage, to make the network convergence faster. The model inherits the trained shared CNN of discriminator to train the DFH model by using many different supervised loss functions not only in the last layer but also in the middle layer of the network. Extensive experiments on two widely used datasets demonstrate that DFH-GAN can generate high-quality binary hash codes and exceed the performance of the state-of-the-art model greatly.

DFH-GAN: A Deep Face Hashing with Generative Adversarial Network

Noisy labels are an unavoidable consequence of labeling processes and detecting them is an important step towards preventing performance degradations in Convolutional Neural Networks. Discarding noisy labels avoids a harmful memorization, while the associated image content can still be exploited in a semi-supervised learning (SSL) setup. Clean samples are usually identified using the small loss trick, i.e. they exhibit a low loss. However, we show that different noise distributions make the application of this trick less straightforward and propose to continuously relabel all images to reveal a discriminative loss against multiple distributions. SSL is then applied twice, once to improve the clean-noisy detection and again for training the final model. We design an experimental setup based on ImageNet32/64 for better understanding the consequences of representation learning with differing label noise distributions and find that non-uniform out-of-distribution noise better resembles real-world noise and that in most cases intermediate features are not affected by label noise corruption. Experiments in CIFAR-10/100, ImageNet32/64 and WebVision (real-world noise) demonstrate that the proposed label noise Distribution Robust Pseudo-Labeling (DRPL) approach gives substantial improvements over recent state-of-the-art. Code is available at https://git.io/JJ0PV.

Towards Robust Learning with Different Label Noise Distributions


Super-resolution aims at increasing the resolution and
level of detail within an image. The current state of the
art in general single-image super-resolution is held
by nESRGAN+,which injects a Gaussian noise after each
residual layer at training time. In this paper, we harness
evolutionary methods to improve nESRGAN+ by optimizing the
noise injection at inference time. More precisely, we use
Diagonal CMA to optimize the injected noise according to a
novel criterion combining quality assessment and realism.
Our results are validated by the PIRM perceptual score and
a human study. Our method outperforms nESRGAN+ on several
standard super-resolution datasets. More generally, our
approach can be used to optimize any method based on noise
injection.

Tarsier: Evolving Noise Injection in Super-Resolution GANs

In this paper, we study the adversarial examples existence and adversarial training from the standpoint of convergence and provide evidence that pointwise convergence in ANNs can explain these observations. The main contribution of our proposal is that it relates the objective of the evasion attacks and adversarial training with concepts already defined in learning theory. Also, we extend and unify some of the other proposals in the literature and provide alternative explanations on the observations made in those proposals. Through different experiments, we demonstrate that the framework is valuable in the study of the phenomenon and is applicable to real-world problems.

Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networks

Real-time semantic segmentation is a challenging task as both segmentation accuracy and inference speed need to be considered at the same time. In this paper, we present a Dual Context Network (DCNet) to address this challenge. It contains two independent sub-networks: Region Context Network and Pixel Context Network. Region Context Network is main network with low-resolution input and feature re-weighting module to achieve sufficient receptive field. Meanwhile, Pixel Context Network with location attention module to capture the location dependencies of each pixel for assisting the main network to recover spatial detail. A contextual feature fusion is introduced to combine output features of these two sub-networks. The experiments show that DCNet can achieve high-quality segmentation while keeping a high speed. Specifically, for Cityscapes test dataset, we achieve 76.1% Mean IOU with the speed of 82 FPS on a single GTX 2080Ti GPU when using ResNet50 as backbone, and 71.2% Mean IOU with the speed of 142 FPS when using ResNet18 as backbone.

Real-time Semantic Segmentation via Region and Pixel Context Network


Obstacle avoidance and environment sensing are crucial
applications in autonomous driving and robotics. Among all
types of sensors, RGB camera is widely used in these
applications as it can offer rich visual contents with
relatively low-cost, and using a single image to perform
depth estimation has become one of the main focuses in
resent research works. However, prior works usually rely on
highly complicated computation and power-consuming GPU to
achieve such task; therefore, we focus on developing a
real-time light-weight system for depth prediction in this
paper. Based on the well-known encoder-decoder
architecture, we propose a supervised learning-based CNN
with detachable decoders that produce depth predictions
with different scales. We also formulate a novel log-depth
loss function that computes the difference of predicted
depth map and ground truth depth map in log space, so as to
increase the prediction accuracy for nearby locations. To
train our model efficiently, we generate depth map and
semantic segmentation with complex teacher models. Via a
series of ablation studies and experiments, it is validated
that our model can efficiently performs real-time depth
prediction with only 0.32M parameters, with the best
trained model outperforms previous works on KITTI dataset
for various evaluation matrices.

Real-time Monocular Depth Estimation withExtremely Light-Weight Neural Network


We address a challenging problem: recognizing mul- tiple text sequences from an image by pure end-to-end learning. It is twofold: 1) Multiple text sequences recognition. Each image may contain multiple text sequences of different content, location and orientation, we try to recognize all these texts in the image. 2) Pure end-to-end (PEE) learning. We solve the problem in a pure end-to-end learning way where each training image is labeled by only text transcripts of the contained sequences, without any geometric annotations.

Recognizing Multiple Text Sequences from an Image by Pure End-To-End Learning

Face recognition has been widely accepted as a means of identification in applications ranging from border control to security in the banking sector. Surprisingly, while widely accepted, we still lack the understanding of uniqueness or distinctiveness of faces as biometric modality. In this work, we study the impact of factors such as image resolution, feature representation, database size, age and gender on uniqueness denoted by the Kullback-Leibler divergence between genuine and impostor distributions. Towards understanding the impact, we present experimental results on the datasets AT&T, LFW, IMDb-Face, as well as ND-TWINS, with the feature extraction algorithms VGGFace, VGG16, ResNet50, InceptionV3, MobileNet and DenseNet121, that reveal the quantitative impact of the named factors. While these are early results, our findings indicate the need for a better understanding of the concept of biometric uniqueness and its implication on face recognition.

How Unique Is a Face: An Investigative Study

Iterative Closest Point (ICP) is one of the mostly used algorithms for 3D point clouds registration. This classical approach can be impacted by the large number of points contained in a point cloud. Planar structures, which are less numerous than points, can be used in well-structured man-made environment.
In this paper we propose a registration method inspired by the ICP algorithm in a plane-based registration approach for indoor environments.
This method is based solely on data acquired with a LiDAR sensor.
A new metric based on plane characteristics is introduced to find the best plane correspondences. The optimal transformation is estimated through a two-step minimization approach, successively performing robust plane-to-plane minimization and non-linear robust point-to-plane registration. 
Experiments on the Autonomous System Labs dataset show that the proposed method enables to successfully register 100% of the scans from the three indoor sequences. Experiments also show that the proposed method is more robust in large motion scenarios than other state-of-the-art algorithms.

A Plane-based Approach for Indoor Point Clouds Registration

Variants of Triplet networks are robust entities for learning a discriminative embedding subspace. There exist different triplet mining approaches for selecting the most suitable training triplets. Some of these mining methods rely on the extreme distances between instances, and some others make use of sampling. However, sampling from stochastic distributions of data rather than sampling merely from the existing embedding instances can provide more discriminative information. In this work, we sample triplets from distributions of data rather than from existing instances. We consider a multivariate normal distribution for the embedding of each class. Using Bayesian updating and conjugate priors, we update the distributions of classes dynamically by receiving the new mini-batches of training data. The proposed triplet mining with Bayesian updating can be used with any triplet-based loss function, e.g., \textit{triplet-loss} or Neighborhood Component Analysis (NCA) loss. Accordingly, Our triplet mining approaches are called Bayesian Updating Triplet (BUT) and Bayesian Updating NCA (BUNCA), depending on which loss function is being used. Experimental results on two public datasets, namely MNIST and histopathology colorectal cancer (CRC), substantiate the effectiveness of the proposed triplet mining method.

Premium content

GazeMAE: General Representations of Eye Movements using a Micro-Macro Autoencoder

Downloads

Next from ICPR 2020

DFH-GAN: A Deep Face Hashing with Generative Adversarial Network

Similar lecture

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