Italy


Semantic segmentation is a challenging and computationally heavy task in computer vision. Recent works have shown promising results applied to real-time semantic segmentation tasks such as autonomous driving cars, scene recognition, and robot navigation systems. In order to maintain fast inference speed, most of the existing networks for real-time semantic segmentation make use of light decoders, or they simply do not use them at all. This strategy helps to maintain their fast inference speed; however, their accuracy performance is significantly lower in comparison to non-real-time semantic segmentation networks. In order to reduce the accuracy gap between real-time and non-real-time segmentation networks, we introduce two key modules aimed to improve the decoder of a high-performance baseline network for real-time semantic segmentation. Our first module, Dilated Asymmetric Pyramidal Fusion (DAPF), is designed to substantially increase the receptive field on the top of the last stage of the encoder, obtaining richer contextual features. Our second module, Multi-resolution Dilated Asymmetric (MDA) module, fuses multi-resolution feature maps coming from both, early and deeper stages of the network, simultaneously refining detail and contextual information in multiple stages of the decoder. Both modules exploit contextual information without excessively increasing the computational complexity of the network. Our proposed network entitled “FASSDNet” reaches 78.8% of mIoU accuracy on Cityscapes validation dataset at 41.1 FPS on full resolution images (1024x2048). In addition, with a lite version of our network, we reach 74.1% of mIoU at 133.1 FPS (full resolution) on a single NVIDIA GTX 1080Ti card with no additional acceleration techniques.

ICPR 2020

Fast and Accurate Real-Time Semantic Segmentation with Dilated Asymmetric Convolutions

hardnet

fully convolutional networks

spatial pyramid pooling

semantic segmentation

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

The edge computing paradigm places compute-capable devices - edge servers - at the network edge to assist mobile devices in executing data analysis tasks. Intuitively, offloading compute-intense tasks to edge servers can reduce their execution time. However, poor conditions of the wireless channel connecting the mobile devices to the edge servers may degrade the overall capture-to-output delay achieved by edge offloading. Herein, we focus on edge computing supporting remote object detection by means of Deep Neural Networks (DNNs), and develop a framework to reduce the amount of data transmitted over the wireless link. The core idea we propose builds on recent approaches splitting DNNs into sections - namely head and tail models - executed by the mobile device and edge server, respectively. The wireless link, then, is used to transport the output of the last layer of the head model to the edge server, instead of the DNN input. Most prior work focuses on classification tasks and leaves the DNN structure unaltered. Herein, our focus is on DNNs for three different object detection tasks, which present a much more convoluted structure, and modify the architecture of the network to: (i) achieve in-network compression by introducing a bottleneck layer in the early layers on the head model, and (ii) prefilter pictures that do not contain objects of interest using a convolutional neural network. Results show that the proposed technique represents an effective intermediate option between local and edge computing in a parameter region where these extreme point solutions fail to provide satisfactory performance. The code and trained models are available at https://github.com/yoshitomo-matsubara/hnd-ghnd-object-detectors .

Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks

Human-object interaction recognition aims for identifying the relationship between a human subject and an object. Researchers incorporate global scene context into the early layers of deep Convolutional Neural Networks as a solution. They report a significant increase in the performance since generally interactions are correlated with the scene (\ie riding bicycle on the city street). However, this approach leads to the following problems. It increases the network size in the early layers, therefore not efficient. It leads to noisy filter responses when the scene is irrelevant, therefore not accurate. 
It only leverages scene context whereas human-object interactions offer a multitude of contexts, therefore incomplete. To circumvent these issues, in this work, we propose Self-Selective Context (SSC). SSC operates on the joint appearance of human-objects and context to bring the most discriminative context(s) into play for recognition. We devise novel contextual features that model the locality of human-object interactions and show that SSC can seamlessly integrate with the State-of-the-art interaction recognition models. Our experiments show that SSC leads to an important increase in interaction recognition performance, while using much fewer parameters.

Self-Selective Context for Interaction Recognition

In this paper, we study the task of facial expression recognition under strong occlusion. We are particularly interested in cases where 50\% of the face is occluded, e.g. when the subject wears a Virtual Reality (VR) headset. While previous studies show that pre-training convolutional neural networks (CNNs) on fully-visible (non-occluded) faces improves the accuracy, we propose to employ knowledge distillation to achieve further improvements. First of all, we employ the classic teacher-student training strategy, in which the teacher is a CNN trained on fully-visible faces and the student is a CNN trained on occluded faces. Second of all, we propose a new approach for knowledge distillation based on triplet loss. During training, the goal is to reduce the distance between an anchor embedding, produced by a student CNN that takes occluded faces as input, and a positive embedding (from the same class as the anchor), produced by a teacher CNN trained on fully-visible faces, so that it becomes smaller than the distance between the anchor and a negative embedding (from a different class than the anchor), produced by the student CNN. Third of all, we propose to combine the distilled embeddings obtained through the classic teacher-student strategy and our novel teacher-student strategy based on triplet loss into a single embedding vector.

We conduct experiments on two benchmarks, FER+ and AffectNet, with two CNN architectures, VGG-f and VGG-face, showing that knowledge distillation can bring significant improvements over the state-of-the-art methods designed for occluded faces in the VR setting. Furthermore, we obtain accuracy rates that are quite close to the state-of-the-art models that take as input fully-visible faces. For example, on the FER+ data set, our VGG-face based on concatenated distilled embeddings attains an accuracy rate of 82.75\% on lower-half-visible faces, which is only 2.24\% below the accuracy rate of a state-of-the-art VGG-13 that is evaluated on fully-visible faces. Given that our model sees only the lower-half of the face, we consider this to be a remarkable achievement. In conclusion, we consider that our distilled CNN models can provide useful feedback for the task of recognizing the facial expressions of a person wearing a VR headset.

Teacher-Student Training and Triplet Loss for Facial Expression Recognition under Occlusion

In this presentation, we mainly show the proposed method in our paper which deal with consistent geolocalization problem. Specifically, we learn motion trajectory with recurrent neural network to achieve geolocalization and propose two strategies solve inconsistent prediction.

Map-Based Temporally Consistent Geolocalization through Learning Motion Trajectories


We present an unsupervised deep learning method for text line segmentation that is inspired by the relative variance between text lines and spaces among text lines. Handwritten text line segmentation is important for the efficiency of further processing. A common method is to train a deep learning network for embedding the document image into an image of blob lines that are tracing the text lines. Previous methods learned such embedding in a supervised manner, requiring the annotation of many document images. This paper presents an unsupervised embedding of document image patches without a need for annotations. The number of foreground pixels over the text lines is relatively different from the number of foreground pixels over the spaces among text lines. Generating similar and different pairs relying on this principle definitely leads to outliers. However, as the results show, the outliers do not harm the convergence and the network learns to discriminate the text lines from the spaces between text lines. Remarkably, with a challenging Arabic handwritten text line segmentation dataset, VML-AHTE, we achieved superior performance over the supervised methods. Additionally, the proposed method was evaluated on the ICDAR 2017 and ICFHR 2010 handwritten text line segmentation datasets.

Unsupervised deep learning for text line segmentation

Transit of wasteful materials within the European
Union is highly regulated through a system of permits. Waste
processing costs vary greatly depending on the waste category of
a permit. Therefore, companies may have a financial incentive to
allege transporting waste with erroneous categorisation.
Our goal is to assist inspectors in selecting potentially manipulated
permits for further investigation, making their task
more effective and efficient. Due to data limitations, a supervised
learning approach based on historical cases is not possible.
Standard unsupervised approaches, such as outlier detection
and data quality-assurance techniques, are not suited since we
are interested in targeting non-random modifications in both
category and category-correlated features.
For this purpose we (1) introduce the concept of crosslier:
an anomalous instance of a category which lies across other
categories; (2) propose eXPose: a novel approach to crosslier
detection based on supervised category modelling; and (3) present
the crosslier diagram: a visualisation tool specifically designed for
domain experts to easily assess crossliers. We compare eXPose
against traditional outlier detection methods in various benchmark
datasets with synthetic crossliers and show the superior
performance of our method in targeting these instances.

The eXPose Approach to Crosslier Detection

Human Pose Estimation is a fundamental task for many applications in the Computer Vision community and it has been widely investigated in the 2D domain, i.e. intensity images.
Therefore, most of the available methods for this task are mainly based on 2D Convolutional Neural Networks and huge manually-annotated RGB datasets, achieving stunning results.
In this paper, we propose RefiNet, a multi-stage framework that regresses an extremely-precise 3D human pose estimation from a given 2D pose and a depth map.
The framework consists of three different modules, each one specialized in a particular refinement and data representation, i.e. depth patches, 3D skeleton and point clouds.
Moreover, we present a new dataset, called Baracca, acquired with RGB, depth and thermal cameras and specifically created for the automotive context.
Experimental results confirm the quality of the refinement procedure that largely improves the human pose estimations of off-the-shelf 2D methods.

RefiNet: 3D Human Pose Refinement with Depth Maps

In a society with increasing age, the understanding of human falls it is of paramount importance. This paper presents a Decision Support System whose pipeline is designed to extract and compute physical domain’s features achieving the state of the art accuracy on the Le2i and UR fall detection datasets. The paper uses the Kinematic Theory of Rapid Human Movement and its sigma-lognormal model together with classic physical features to achieve 98% and 99% of accuracy in automatic fall detection on respectively Le2i and URFD datasets. The effort made in the design of this work is toward recognition of falls by using physical models whose laws are clear and understandable.

Fall Detection by Human Pose Estimation and Kinematic Theory

The availability of large-scale annotated datasets has enabled Fully-Convolutional Neural Networks to reach outstanding performance on road extraction in aerial images. However, high-quality pixel-level annotation is expensive to produce and even manually labeled data often contains topological errors. Trading off quality for quantity, many datasets rely on already available yet noisy labels, for example from OpenStreetMap.
In this paper, we explore the training of custom U-Nets built with ResNet and DenseNet backbones using noise-aware losses that are robust towards label omission and registration noise. We perform an extensive evaluation of standard and noise-aware losses, including a novel Bootstrapped DICE-Coefficient loss, on two challenging road segmentation benchmarks. Our losses yield a consistent improvement in overall extraction quality and exhibit a strong capacity to cope with severe label noise. Our method generalizes well to two other fine-grained topology delineation tasks: surface crack detection for quality inspection and cell membrane extraction in electron microscopy imagery.

Aerial Road Segmentation in the Presence of Topological Label Noise


Document images dewarping is still a challenge especially when documents are captured with one camera in an uncontrolled environment. In this paper we propose a generic approach based on vanishing points (VP) to reconstruct the 3D shape of document pages. Unlike previous methods we do not need to segment the text included in the documents. Therefore, our approach is less sensitive to pre-processing and segmentation errors. The computation of the VPs is robust and relies on the a-contrario framework, which has only one parameter whose setting is based on probabilistic reasoning instead of experimental tuning. Thus, our method can be applied to any kind of document including text and non-text blocks and extended to other kind of images. Experimental results show that the proposed method is robust to a variety of distortions.

Downloads

Next from ICPR 2020

Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks

Similar lecture

Semantic Segmentation Refinement Using Entropy and Boundary-guided Monte Carlo Sampling and Directed Regional Search