Italy

Obtaining a meaningful, interpretable yet compact representation of the immediate surroundings of an autonomous vehicle is paramount for effective operation as well as safety. This paper proposes a solution to this by representing semantically important objects from a top-down, ego-centric bird’s eye view. The novelty in this work is from formulating this problem as an adversarial learning task, tasking a generator model to produce bird’s eye view representations which are plausible enough to be mistaken as a ground truth sample. This is achieved by using a Wasserstein Generative Adversarial Network based model conditioned on object detections from monocular RGB images and the corresponding bounding boxes. Extensive experiments show our model is more robust to novel data compared to strictly supervised benchmark models, while being a fraction of the size of the next best.

ICPR 2020

DeepBEV: A Conditional Adversarial Network for Bird&#39;s Eye View Generation

vision for robotics

learning-based vision

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. 


DeepBEV: A Conditional Adversarial Network for Bird's Eye View Generation

poster

Active learning emerged as an alternative to alleviate
the effort to label huge amount of data for data-hungry applications (such as image/video indexing and retrieval, autonomous
driving, etc.). The goal of active learning is to automatically select
a number of unlabeled samples for annotation (according to a
budget), based on an acquisition function, which indicates how
valuable a sample is for training the model. The learning loss
method is a task-agnostic approach which attaches a module
to learn to predict the target loss of unlabeled data, and
select data with the highest loss for labeling. In this work,
we follow this strategy but we define the acquisition function
as a learning to rank problem and rethink the structure of
the loss prediction module, using a simple but effective listwise
approach. Experimental results on four datasets demonstrate that
our method outperforms recent state-of-the-art active learning
approaches for both image classification and regression tasks.

Learning to Rank for Active Learning: A Listwise
Approach


This paper addresses the problem of selecting appearance features for multiple object tracking (MOT) in urban scenes. Over the years, a large number of features has been used for MOT. However, it is not clear whether some of them are better than others. Commonly used features are color histograms, histograms of oriented gradients, deep features from convolutional neural networks and re-identification (ReID) features. In this study, we assess how good these features are at discriminating objects enclosed by a bounding box in urban scene tracking scenarios. Several affinity measures, namely the L1, L2 and the Bhattacharyya distances, Rank-1 counts and the cosine similarity, are also assessed for their impact on the discriminative power of the features. Results on several datasets show that features from ReID networks are the best for discriminating instances from one another regardless of the quality of the detector. If a ReID model is not available, color histograms may be selected if the detector has a good recall and there are few occlusions; otherwise, deep features are more robust to detectors with lower recall.

An Empirical Analysis of Visual Features for Multiple Object Tracking in Urban Scenes


Zero-Shot Learning(ZSL) techniques could classify
a completely unseen class, which it has never seen before
during training. Thus, making it more apt for any real-life
classification problem, where it is not possible to train a system
with annotated data for all possible class types. This work
investigates recognition of word images written in Bengali Script
in a ZSL framework. The proposed approach performs Zero-Shot
word recognition by coupling deep learned features procured
from various CNN architectures along with 13 basic shapes/stroke
primitives commonly observed in Bengali script characters. As
per the notion of ZSL framework those 13 basic shapes are
termed as “Signature/Semantic Attributes”. The obtained results
are promising while evaluation was carried out in a Five-
Fold cross-validation setup dealing with samples from 250 word
classes.

Recognizing Bengali Word Images - A Zero-Shot
Learning Perspective


Object detection based on convolutional neural networks is a hot research topic in computer vision. The illumination component in the image has a great impact on object detection, and it will cause a sharp decline in detection performance under low-light conditions. Using low-light image enhancement technique as a pre-processing mechanism can improve image quality and obtain better detection results. However, due to the complexity of low-light environments, the existing enhancement methods may have negative effects on some samples. Therefore, it is difficult to improve the overall detection performance in low-light conditions. In this paper, our goal is to use image enhancement to improve object detection performance rather than perceptual quality for humans. We propose a novel framework that combines low-light enhancement and object detection for end-to-end training. The framework can dynamically select different enhancement subnetworks for each sample to improve the performance of the detector. Our proposed method consists of two stage: the enhancement stage and the detection stage. The enhancement stage dynamically enhances the low-light images under the supervision of several enhancement methods and output corresponding weights. During the detection stage, the weights offers information on object classification to generate high-quality region proposals and in turn result in accurate detection. Our experiments present promising results, which show that the proposed method can significantly improve the detection performance in low-light environment.

Dynamic Low-Light Image Enhancement for Object Detection via End-to-End Training

We present several extensions to an existing two-stage architecture for segmentation-based industrial defect detection. We enable end-to-end training by careful balancing of both losses and by manipulating gradient flow through the networks during learning. Employing weighted segmentation loss by applying the distance transform algorithm to the coarse region-based labels allows us to reduce the annotation requirements. Frequency-of-use based sampling scheme is used to address the issues of sampling in heavily unbalanced datasets. Combining all the extensions allows the proposed method to achieve a 100% detection rate on two surface defect detection tasks. We perform an extensive ablation study of our contributions on three datasets.

End-to-end training of a two-stage neural network for defect detection

Passive wireless sensing using WiFi signals has become a very active area of research over the past few years. Such techniques provide a cost-effective and non-intrusive solution for human activity sensing especially in healthcare applications. One of the main approaches used in wireless sensing is based on fine-grained WiFi Channel State Information (CSI) which can be extracted from commercial Network Interface Cards (NICs). In this paper, we present a new signal processing pipeline required for effective wireless sensing. An experiment involving five participants performing six different activities was carried out in an office space to evaluate the performance of activity recognition using WiFi CSI in different physical layouts. Experimental results show that the CSI system has the best detection performance when activities are performed half-way in between the transmitter and receiver in a line-of-sight (LoS) setting. In this case, an accuracy as high as 91% is achieved while the accuracy for the case where the transmitter and receiver are co-located is around 62%. As for the case when data from all layouts is combined, which better reflects the real-world scenario, the accuracy is around 67%. The results showed that the activity detection performance is dependent not only on the locations of the transmitter and receiver but also on the positioning of the person performing the activity.

Translation Resilient Opportunistic WiFi Sensing

Image-to-image translation with Deep Learning neural networks, particularly with Generative Adversarial Networks (GANs), is one of the most powerful methods for simulating astronomical images. However, current work is limited to utilizing paired images with supervised translation, and there has been rare discussion on reconstructing noise background that encodes instrumental and observational effects. These limitations might be harmful for subsequent scientific applications in astrophysics. Therefore, we aim to develop methods for using unpaired images and preserving noise characteristics in image translation. In this work, we propose a two-way image translation model using GANs that exploits both paired and unpaired images in a semi-supervised manner, and introduce a noise emulating module that is able to learn and reconstruct noise characterized by high-frequency features. By experimenting on multi-band galaxy images from the Sloan Digital Sky Survey (SDSS) and the Canada France Hawaii Telescope Legacy Survey (CFHT), we show that our method recovers global and local properties effectively and outperforms benchmark image translation models. To our best knowledge, this work is the first attempt to apply semi-supervised methods and noise reconstruction techniques in astrophysical studies.

Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks

One of the main challenges of visual question answering (VQA) lies in properly reasoning relations among visual regions involved in the question. In this paper, we propose a novel neural network to perform question-guided relational reasoning in multi-scales for visual question answering, in which each region of image is enhanced by regional attention. 
Specifically, we present regional attention module, which consists of a soft attention module and a hard attention module, to select informative regions of the image according to informative evaluations implemented by question-guided soft attention. Combinations of different informative regions are then concatenated with question embedding in different scales to capture relational information. Relational reasoning module can extract question-based relational information among regions, in which multi-scale mechanism gives it the ability to model scaled relationships and makes it sensitive to numbers. We conduct experiments to show that our proposed architecture is effective and achieves competitive results VQA v2. 



Multi-scale Relational Reasoning with Regional Attention for Visual Question Answering


The massive adoption of social networks has made available an unprecedented amount of user-generated content, which may be analyzed in order to determine people's opinions and emotions on a large variety of topics. Research has made many efforts in defining accurate algorithms for the analysis of emotions conveyed by texts, however their performance often relies on the existence of large annotated datasets, whose current scarcity represents a major issue.
The manual creation of such datasets represents a costly and time-consuming activity and hence there is an increasing demand for techniques for the automatic annotation of corpora.
In this work we present a methodology for the automatic annotation of video subtitles on the basis of the analysis of facial expressions of people in videos, with the goal of creating annotated corpora that may be used to train emotion recognition algorithms. Facial expressions are analyzed through machine learning algorithms, on the basis of a set of manually-engineered facial features that are extracted from video frames. The soundness of the proposed methodology has been evaluated through an extensive experimentation aimed at determining the performance on real datasets of each methodological step.

Automatic Annotation of Corpora for Emotion Recognition Through Facial Expression Analysis

Clustering is an unsupervised machine learning method giving insights on data without early knowledge. Classes of data are return by assembling similar elements together. Giving the increasing of the available data, this method is now applied in a lot of fields with various data types. Here, we propose to explore the case of time series clustering. Indeed, time series are one of the most classic data type, and are present in various fields such as medical or finance. This kind of data can be pre-processed by of dimension reduction methods, such as the recent UMAP algorithm. In this paper, a benchmark of time series clustering is created, comparing the results with and without UMAP as a pre-processing step. UMAP is used to enhance clustering results. For completeness, three different clustering algorithms and two different geometric representation for the time series (Classic Euclidean geometry, and Riemannian geometry on the Stiefel Manifold) are applied. The results are compared with and without UMAP as a pre-processing step on the databases available at UCR Time Series Classification Archive.

Premium content

DeepBEV: A Conditional Adversarial Network for Bird's Eye View Generation

Downloads

Next from ICPR 2020

Learning to Rank for Active Learning: A Listwise Approach

Similar lecture

Yolo+FPN: 2D and 3D Fused Object Detection with an RGB-D Camera