Italy

Deep reinforcement learning (DRL) has achieved great success in processing vision-based driving tasks. However, the end-to-end training manner makes DRL agents suffer from overfitting training scenes. The agents easily fail to generalize to unseen environments. In this paper, we propose a deep reinforcement learning for autonomous driving by transferring visual features. We formulate the DRL training as a perception and control module and introduce adversarial training mechanism for autonomous driving. The perception module is able to extract invariant features between different domains through adversarial training. While the DRL agent can then be trained on the basis of low dimensional states. In this manner, the proposed approach enables trained agents to adapt to unseen environments by learning robust features invariant across various scenes. We evaluate the proposed approach by transferring visual features between different simulators. The experimental results demonstrate the driving policy trained in the source domain can be directly applied in the target domain, and achieve great efficient and effective performance for autonomous driving.

ICPR 2020

Deep Reinforcement Learning for Autonomous Driving by Transferring Visual Features

autonomous driving

deep reinforcement learning

transfer 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

For diagnosis and risk assessment in patients with stable ischemic heart disease, myocardial perfusion scintigraphy is one of the most common cardiological examinations performed today. There are however many motivations for why an artificial intelligence algorithm would provide useful input to this task. For example to reduce the subjectiveness and save time for the nuclear medicine physicians working with this time consuming task. In this work we have developed a deep learning algorithm for multi-label classification based on a convolutional neural network to estimate the probability of obstructive coronary artery disease in the left anterior artery, left circumflex artery and right coronary artery. The prediction is based on data from myocardial perfusion scintigraphy studies conducted in a dedicated Cadmium-Zinc-Telluride cardio camera (D-SPECT Spectrum Dynamics). Data from 588 patients was available, with stress images in both upright and supine position, as well as a number of auxiliary parameters such as angina symptoms and age. The data was used to train and evaluate the algorithm using 5-fold cross-validation. We achieve state-of-the-art results for this task with an area under the receiver operating characteristics curve of 0.89 as average on per-vessel level and 0.95 on per-patient level.

Prediction of Obstructive Coronary Artery Disease from Myocardial Perfusion Scintigraphy using Deep Neural Networks

Seismocardiogram (SCG) has become easily accessible in the past decade owing to the advance of sensor technology. However, SCG biometric has not been widely explored. In this paper, we propose combining wavelet transform together with deep learning models, machine learning classifiers, or distance metric to perform SCG biometric matching tasks. We validate the proposed methods on the publicly available dataset from PhysioNet database. The dataset contains one hour long electrocardiogram, breathing, and SCG data of 20 subjects. We train the models on the first five minute SCG and conduct identification on the last five minute SCG. We evaluate the identification and authentication performance with recognition rate and equal error rate, respectively. Based on the results, we show that wavelet transformed SCG biometric can achieve state-of-the-art performance when combined with deep learning models, machine learning classifiers, or structural similarity metric.


Exploring Seismocardiogram Biometrics with Wavelet Transform

An advanced simulation framework has recently been introduced for exploring human perception and visuomotor control. In this context, we investigate locally-connected, irregular deep neural networks (liNets) for biomimetic active vision. Like commonly used CNNs, liNets are locally-connected, forming receptive fields, but unlike CNNs, they are suitable for spatially irregular photoreceptor distributions inspired by those found in foveated biological retinas. Compared to fully connected
deep neural networks, liNets accommodate a much greater number of retinal photoreceptors to enhance visual acuity without intractable memory consumption. LiNets serve well in the biomimetic active vision system embodied in a simulated human that learns active visuomotor control and active appearance based recognition.

Locally-Connected, Irregular Deep Neural Networks for Biomimetic Active Vision in a Simulated Human

In this paper, we propose an occlusion-robust pose estimation method of an unknown object instance in an object category from a depth image. In a cluttered environment, objects are often occluded mutually. For estimating the pose of an object in such a situation, a method that de-occludes the unobservable area of the object would be effective. However, there are two difficulties; occlusion causes the offset between the center of the actual object and its observable area, and different instances in a category may have different shapes. To cope with these difficulties, we propose a two-stage Encoder-Decoder model to extract features with objects whose centers are aligned to the image center. In the model, we also propose the Median-shape Reconstructor as the second stage to absorb shape variations in a category. By evaluating the method with both a large-scale virtual dataset and a real dataset, we confirmed the proposed method achieves good performance on pose estimation of an occluded object from a depth image.

Median-shape Representation Learning for Category-level Object Pose Estimation in Cluttered Environments

Graphical models allow to describe the interplayamong variables of a system through a compact representation,suitable when relations evolve over time. For example, in abiological setting, genes interact differently depending on externalenvironmental or metabolic factors. To incorporate this dynamicsa viable strategy is to estimate a sequence of temporally relatedgraphs assuming similarity among samples in different timepoints. While adjacent time points may direct the analysistowards a robust estimate of the underlying graph, the resultingmodel will not incorporate long-term or recurrent temporalrelationships. In this work we propose a dynamical networkinference model that leverages on kernels to consider generaltemporal patterns (such as circadian rhythms or seasonality). Weshow how our approach may also be exploited when the recurrentpatterns are unknown, by coupling the network inference with aclustering procedure that detects possibly non-consecutive similarnetworks. Such clusters are then used to build similarity kernels.The convexity of the functional is determined by whether weimpose or infer the kernel. In the first case, the optimisationalgorithm exploits efficiently proximity operators with closed-form solutions. In the other case, we resort to an alternatingminimisation procedure which jointly learns the temporal kerneland the underlying network. Extensive analysis on syntheticdata shows the efficacy of our models compared to state-of-the-art methods. Finally, we applied our approach on two real-world applications to show how considering long-term patternsis fundamental to have insights on the behaviour of a complexsystem.

Temporal Pattern Detection in Time-Varying Graphical Models


We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach uses an arbitrary end-to-end text recognition system to obtain text region proposals and their, possibly erroneous, transcriptions. The method includes matching of imprecise transcriptions to weak annotations and an edit distance guided neighbourhood search. It produces nearly error-free, localised instances of scene text, which we treat as "pseudo ground truth" (PGT).

The method is applied to two weakly-annotated datasets. Training with the extracted PGT consistently improves the accuracy of a state of the art recognition model, by 3.7% on average, across different benchmark datasets (image domains) and 24.5% on one of the weakly annotated datasets.

Text Recognition: Real World Data and Where to Find Them

Multi-camera sports players' 3D localization is always a challenging task due to heavy occlusions in crowded sports scenes. Traditional methods can only provide players’ locations without identifying information. Existing methods of localization may cause ambiguous detection and unsatisfactory precision and recall, especially when heavy occlusions occur. To solve this problem, we propose a generic localization method by providing distinguishable results that have the probabilities of locations being occupied by players with unique ID labels. We design the algorithms with a multi-dimensional Bayesian model to create a Probabilistic and Identified Occupancy Map (PIOM). By using this model, we jointly apply deep learning-based object segmentation and identification to obtain sports players’ probable positions and their likely identification labels. This approach not only provides players 3D locations but also gives their ID information that is distinguishable from others. Experimental results demonstrate that our method outperforms the previous localization approaches with reliable and distinguishable outcomes.

Multi-camera Sports Players 3D Localization with Identification Reasoning

We introduce a new deep architecture for closing the semantic gaps between the multiscale feature maps. The proposed ScarfNet generates new multiscale feature maps with deeply fused and redistributed semantics by using the combination of biLSTM and the channel-wise attention model. Our evaluation results show that our method offers significant improvement over the baseline detectors as well as other competitive detectors.


ScarfNet: Multi-scale Features with Deeply Fused and Redistributed Semantics for Enhanced Object Detection


Automatic facial expression recognition (FER) has gained much attention due to its applications in human-computer interaction. Among the approaches to improve FER tasks, this paper focuses on deep architecture with the attention mechanism. We propose a novel Masking Idea to boost the performance of CNN in facial expression task. It uses a segmentation network to refine feature maps, enabling the network to focus on relevant information to make correct decisions. In experiments, we combine the ubiquitous Deep Residual Network and Unetlike architecture to produce a Residual Masking Network. The proposed method holds state-of-the-art (SOTA) accuracy on the well-known FER2013 and private VEMO datasets

Facial Expression Recognition Using Residual Masking Network


Photo-to-caricature translation aims to synthesize the caricature as a rendered image exaggerating the features through sketching, pencil strokes, or other artistic drawings. Style rendering and geometry deformation are the most important aspects in photo-to-caricature translation task. To take both into consideration, we propose an unsupervised contrastive photo-to-caricature translation architecture. Considering the intuitive artifacts in the existing methods, we propose a contrastive style loss for style rendering to enforce the similarity between the style of rendered photo and the caricature, and simultaneously enhance its discrepancy to the photos. To obtain an exaggerating deformation in an unpaired/unsupervised fashion, we propose a Distortion Prediction Module (DPM) to predict a set of displacements vectors for each input image while fixing some controlling points, followed by the thin plate spline interpolation for warping. The model is trained on unpaired photo and caricature while can offer bidirectional synthesizing via inputting either a photo or a caricature. Extensive experiments demonstrate that the proposed model is effective to generate hand-drawn like caricatures compared with existing competitors.

Premium content

Deep Reinforcement Learning for Autonomous Driving by Transferring Visual Features

Downloads

Next from ICPR 2020

Prediction of Obstructive Coronary Artery Disease from Myocardial Perfusion Scintigraphy using Deep Neural Networks

Similar lecture

Self-supervised Learning for Astronomical Image Classification