Italy

Face normalization can be a crucial step when handling generic face recognition. We propose the Pose and Illumination Normalization (PIN) framework with contrast data learning for face normalization. The PIN framework is designed to learn the transformation from a source set to a target set. The source set and the target set compose a contrastive data set for learning. The source set contains faces collected in the wild and thus covers a wide range of variation across illumination, pose, expression and other variables. The target set contains face images taken under controlled conditions and all faces are in frontal pose and balanced in illumination. The PIN framework is composed of an encoder, a decoder and two discriminators. The encoder is made of a state-of-the-art face recognition network and acts as a facial feature extractor, which is not updated during training. The decoder is trained on both the source and target sets, and aims to learn the transformation from the source set to the target set; and therefore, it can transform an arbitrary face into a illumination and pose normalized face. The discriminators are trained to ensure the photo-realistic quality of the normalized face images generated by the decoder. The loss functions employed in the decoder and discriminators are appropriately designed and weighted for yielding better normalization outcomes and recognition performance. We verify the performance of the propose framework on several benchmark databases, and compare with state-of-the-art approaches.

ICPR 2020

Contrastive Data Learning for Facial Pose and Illumination Normalization

face normalization

face recognition

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


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.

JECL: Joint Embedding and Cluster Learning for Image-Text Pairs


As a challenging task of Natural Language Processing(NLP), zero-shot text classification has attracted more and more attention recently. It aims to detect classes that the model has never seen in the training set. For this purpose, a feasible way is to construct a connection between the seen and unseen classes by semantic extension and classify the unseen classes by information propagation over the connection. Although many related zero-shot text classification methods have been exploited, how to realize semantic extension properly and propagate information effectively are far from solved. In this paper, we propose a novel zero-shot text classification method called Semantically Extended Graph Convolutional Network (SEGCN). In the proposed method, the semantic category knowledge from ConceptNet is utilized to semantic extension for linking seen classes to unseen classes and constructing a graph of all categories. Then, we build upon Graph Convolutional Network (GCN) for predicting the textual classifier for each category, which transfers the category knowledge by the convolution operators on the constructed graph and is trained in a semi-supervised manner using the samples of the seen classes. The experimental results on Dbpedia and 20newsgroup datasets show that our method outperforms the state of the art zero-shot text classification methods.

Zero-Shot Text Classification with Semantically Extended Graph Convolutional Network

Building footprint extraction in remote sensing data
benefits many important applications, such as urban
planning and population estimation. Recently, rapid
development of Convolutional Neural Networks (CNNs) and
open-sourced high resolution satellite building image
datasets have pushed the performance boundary further for
automated building extractions. However, CNN approaches
often generate imprecise building morphologies including
noisy edges and round corners. In this paper, we leverage
the performance of CNNs, and propose a module that uses
prior knowledge of building corners to create angular and
concise building polygons from CNN segmentation outputs. We
describe a new transform, Relative Gradient Angle Transform
(RGA Transform) that converts object contours from time vs.
space to time vs. angle. We propose a new shape descriptor,
Boundary Orientation Relation Set (BORS), to describe angle
relationship between edges in RGA domain, such as
orthogonality and parallelism. Finally, we develop an
energy minimization framework that makes use of the angle
relationship in BORS to straighten edges and reconstruct
sharp corners, and the resulting corners create a polygon.
Experimental results demonstrate that our method refines
CNN output from a rounded approximation to a more clear-cut
angular shape of the building footprint.

Quantization in Relative Gradient Angle Domain For Building Polygon Estimation

For image ranking tasks with naturally continuous output, such as age and scenicness estimation, it is common to discretize the label range and apply methods from (ordered)classification analysis. In this paper, we propose a data-driven approach for simultaneous representation learning and label discretization. Compared to arbitrarily selecting thresholds, we seek to learn thresholds and image representations by minimizing a novel loss function in an end-to-end model. We demonstrate our combined approach on a variety of image ranking tasks and demonstrate that it outperforms task-specific methods. Additionally, our learned partitioning scheme can be transferred to improve methods that rely on discretization.

Learning Natural Thresholds for Image Ranking

Revisiting GNN: Graph Filtering Perspective

GAP: Quantifying the Generative Adversarial Set and Class Feature Applicability of Deep Neural Networks

Pedestrian lane detection is a core component in many assistive and autonomous navigation systems. These systems are usually deployed in environments that require real-time processing. Many state-of-the-art deep neural networks only focus on detection accuracy but not inference speed. Without further modifications, they are not suitable for real-time applications. Furthermore, the task of designing a high-performing deep neural network is time-consuming and requires experience. To tackle these issues, we propose a neural architecture search algorithm that can find the best deep network for pedestrian lane detection automatically. The proposed method searches in a network-level space using the gradient descent algorithm. Evaluated on a dataset of 5,000 images, the deep network found by the proposed algorithm achieves comparable segmentation accuracy, while being significantly faster than other state-of-the-art methods. The proposed method has been successfully implemented as a real-time pedestrian lane detection tool.

Real-time Pedestrian Lane Detection for Assistive Navigation using Neural Architecture Search

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


Modern Convolutional Neural Networks~(CNNs) have been improving the accuracy of person re-identification (re-id) using a large number of training samples.
Such a re-id system suffers from a lack of training samples for deployment to practical security applications. To address this problem, we focus on the approach that transfers features of a CNN pre-trained on a large-scale person re-id dataset to a small-scale dataset. Most of the existing CNN feature transfer methods use the features of fully connected layers that entangle locally pooled features of different spatial locations on an image. 
Unfortunately, due to the difference of view angles and the bias of walking directions of the persons, each camera view in a dataset has a unique spatial property in the person image, which reduces the generality of the local pooling for different cameras/datasets. 
To account for the camera- and dataset-specific spatial bias, we propose a method to learn camera and dataset-specific position weight maps for discriminative local pooling of convolutional features. 
Our experiments on four public datasets confirm the effectiveness of the proposed feature transfer with a small number of training samples in the target datasets.


Convolutional Feature Transfer via Camera-Specific Discriminative Pooling for Person Re-Identification

We present a Multi-Features Siamese Tracker (MFST), a novel tracking algorithm exploiting several hierarchical feature maps for robust deep similarity tracking. Since Convolutional layers provide several abstraction levels in characterizing an object, fusing hierarchical features allows to ensure a richer and more efficient representation. Moreover, we handle the target appearance variation by calibrating deep features extracted from two different CNN models. Based on this advanced feature representation, our method achieves high tracking accuracy, while outperforming standard Siamese trackers on object tracking benchmarks.

Downloads

Next from ICPR 2020

JECL: Joint Embedding and Cluster Learning for Image-Text Pairs

Similar lecture

Anglar Sparsemax for Face Recognition