Italy

Novel view synthesis is a challenging problem in computer vision and robotics. Different from the existing works, which need the reference images or 3D models of the scene to generate images under novel views, we propose a novel paradigm to this problem. That is, we synthesize the novel view from only a 6-DoF camera pose directly. Although this setting is the most straightforward way, there are few works addressing it. While, our experiments demonstrate that, with a concise CNN, we could get a meaningful parametric model that could reconstruct the correct scenery images only from the 6-DoF pose. To this end, we propose a two-stage learning strategy, which consists of two consecutive CNNs: GenNet and RefineNet. GenNet generates a coarse image from a camera pose. RefineNet is a generative adversarial network that refines the coarse image. In this way, we decouple the geometric relationship between mapping and texture detail rendering. Extensive experiments conducted on the public datasets prove the effectiveness of our method. We believe this paradigm is of high research and application value and could be an important direction in novel view synthesis.

ICPR 2020

Novel View Synthesis from only a 6-DoF Camera Pose by Two-stage Networks

6-dof camera pose

novel view synthesis

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

Research on facial action unit detection has shown remarkable performances by using deep spatial learning models in recent years, however, it is far from reaching its full capacity in learning due to the lack of use of temporal information of AUs across time. Since the AU occurrence in one frame is highly likely related to previous frames in a temporal sequence, exploring temporal correlation of AUs across frames becomes a key motivation of this work. In this paper, we propose a novel temporal fusion and AU-supervised self-attention network (a so- called SAT-Net) to address the AU detection problem. First of all, we input the deep features of a sequence into a convolutional LSTM network and fuse the previous temporal information into the feature map of the last frame, and continue to learn the AU occurrence. Second, considering the AU detection problem is a multi-label classification problem that individual label depends only on certain facial areas, we propose a new self-learned attention mask by focusing the detection of each AU on parts of facial areas through the learning of individual attention mask for each AU, thus increasing the AU independence without the loss of any spatial relations. Our extensive experiments show that the proposed framework achieves better results of AU detection over the state-of-the-arts on two benchmark databases (BP4D and DISFA).

SAT-Net: Self-Attention and Temporal Fusion for Facial Action Unit Detection

Deep learning classifiers are now known to have flaws in the representations of their class. Adversarial attacks can find a human-imperceptible perturbation for a given image that will mislead a trained model. The most effective methods to defend against such attacks trains on generated adversarial examples to learn their distribution. 
Previous work aimed to align original and adversarial image representations in the same way as domain adaptation to improve robustness. Yet, they partially align the representations using approaches that do not reflect the geometry of space and distribution.
In addition, it is difficult to accurately compare robustness between defended models. Until now, they have been evaluated using a fixed perturbation size. However, defended models may react differently to variations of this perturbation size.
In this paper, the analogy of domain adaptation is taken a step further by exploiting optimal transport theory. We propose to use a loss between distributions that faithfully reflect the ground distance. This leads to SAT (Sinkhorn Adversarial Training), a more robust defense against adversarial attacks.
Then, we propose to quantify more precisely the robustness of a model to adversarial attacks over a wide range of perturbation sizes using a different metric, the Area Under the Accuracy Curve (AUAC). We perform extensive experiments on both CIFAR-10 and CIFAR-100 datasets and show that our defense is globally more robust than the state-of-the-art.

Optimal Transport As a Defense against Adversarial Attacks

Analysis of longitudinal changes in brain diseases is essential for a better characterization of pathological processes and evaluation of the prognosis. This is particularly important in Multiple Sclerosis (MS) which is the first traumatic disease in young adults, with unknown etiology and characterized by complex inflammatory and degenerative processes leading to different clinical courses. In this work, we propose a fully automated tensor-based algorithm for the classification of MS clinical forms based on the structural connectivity graph of the white matter (WM) network. Using non-negative tensor factorization (NTF), we first focused on the detection of pathological patterns of the brain WM network affected by significant longitudinal variations. Second, we performed unsupervised classification of different MS phenotypes based on these longitudinal patterns, and finally, we used the latent factors obtained by the factorization algorithm to identify the most affected brain regions.

Tensor Factorization of Brain Structural Graph for Unsupervised Classification in Multiple Sclerosis


In this talk we present a novel defogging technique, named CurL-Defog, aimed at minimizing the creation of unwanted artifacts during the defogging process. The majority of learning based defogging approaches rely on paired data (i.e., the same images with and without fog), where fog is artificially added to clear images: this often provides good results on mildly fogged images but does not generalize well to real difficult cases. On the other hand, the models trained with real unpaired data (e.g. CycleGAN) can provide visually impressive results but they often produce unwanted artifacts. In this paper we propose a curriculum learning strategy coupled with an enhanced CycleGAN model in order to reduce the number of produced artifacts, while maintaining state-of-the-art performance in terms of contrast enhancement and image reconstruction. We also introduce a new metric, called HArD (Hazy Artifact Detector) to numerically quantify the amount of artifacts in the defogged images, thus avoiding the tedious and subjective manual inspection of the results. The proposed approach compares favorably with state-of-the-art techniques on both real and synthetic datasets.


Towards Artifact-Free Image Defogging

High quality perception is essential for autonomous driving (AD) systems. To reach the accuracy and robustness that are required by such systems, several types of sensors must be combined. Currently, mostly cameras and laser scanners (lidar) are deployed to build a representation of the world around the vehicle. While radar sensors have been used for a long time in the automotive industry, they are still under-used for AD despite their appealing characteristics (notably, their ability to measure the relative speed of obstacles and to operate even in adverse weather conditions). To a large extent, this situation is due to the relative lack of automotive datasets with real radar signals that are both raw and annotated. In this work, we introduce CARRADA, a dataset of synchronized camera and radar recordings with range-angle-Doppler annotations. We also present a semi-automatic annotation approach, which was used to annotate the dataset, and a radar semantic segmentation baseline, which we evaluate on several metrics.

CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations


Computation of the orthogonal distance from a given point to an ellipse is the basis of orthogonal distance based ellipse fitting methods. The problem of this orthogonal distance and the corresponding orthogonal contacting point on the ellipse is investigated, and two algorithms, the exact one and the convergent iterative one, are proposed. The exact algorithm utilizes the closed form solution of quartic equations, but is numerically unstable. The iterative algorithm, however, uses Newton’s method to solve the equation, and starts from an initial solution that is proven to lead to a convergent iteration. The proposed algorithms are compared in experiments with an existing rival. Although the rival algorithm is slightly faster and more accurate in realistic scenarios, divergence is likely to occur. On the other hand, both our exact and iterative algorithms can reliably produce the solution needed. While the exact algorithm encounters numeric instability, the iterative algorithm is only slightly outperformed by the existing rival in speed and accuracy, but at the same time provides more reliable computation process, thus making it a preferable method for the task.

Exact and Convergent Iterative Methods to Compute the Orthogonal Point-to-Ellipse Distance

Machine learning driven object detection and classification within non-visible imagery has an important role in many fields such as night vision, all-weather surveillance and aviation security. However, such applications often suffer due to the limited quantity and variety of non-visible spectral domain imagery, in contrast to the high data availability of visible-band imagery that readily enables contemporary deep learning driven detection and classification approaches. To address this problem, this paper proposes and evaluates a novel data augmentation approach that leverages the more readily available visible-band imagery via a generative domain transfer model. The model can synthesise large volumes of non-visible domain imagery by image-to-image (I2I) translation from the visible image domain. Furthermore, we show that the generation of interpolated mixed class (non-visible domain) image examples via our novel Conditional CycleGAN Mixup Augmentation (C2GMA) methodology can lead to a significant improvement in the quality of non-visible domain classification tasks that otherwise suffer due to limited data availability. Focusing on classification within the Synthetic Aperture Radar (SAR) domain, our approach is evaluated on a variation of the Statoil/C-CORE Iceberg Classifier Challenge dataset and achieves 75.4% accuracy, demonstrating a significant improvement when compared against traditional data augmentation strategies (Rotation, Mixup, and MixCycleGAN).

Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery

The target of our proposed method is to optimize the shape of airfoil geometries to fulfill some given fluid dynamical quantities, which are acting as physical constraints for the optimization process e.g., forces or the pressure difference can be used as constraints. In the first step, a U-Net is trained to learn the underlying fluid dynamics to infer the flow field from a given input geometry. In the second step, a Spatial Transformer Network (STN) is stacked in front of the U-Net to optimize the shape of an initial input geometry, such that the output geometry fulfills the physical constraints.


Transferable Model for Shape Optimization subject to Physical Constraints

Wrist-wearable devices such as smartwatch have gained popularity as they provide quick access to various information and easy access to multiple applications. Among the smartwatch applications, user verification based on the handwriting is gaining momentum by considering its reliability and user-friendliness. In this paper, we present a novel technique for user verification using a smartwatch based on a writing pattern or style. The proposed approach leverages accelerometer data captured from the smartwatch that is further represented using 2D Continuous Wavelet Transform (CWT) and deep features extracted using the pre-trained ResNet50. These features are classified using the ensemble of the classifier to make the final decision on user verification. Extensive experiments are carried out on the newly captured dataset using two different smartwatches with three different writing scenarios (or activities). Experimental results provide critical insights and analysis of the results in such a verification scenario.

Handwritten Signature and Text based User Verification using Smartwatch

Nowadays, in the area of autonomous driving, the computational power of the object detectors is limited by the embedded devices and the public datasets for autonomous driving are over-idealistic. In this paper, we propose a pipeline combining both block-wise pruning and channel-wise pruning to compress the object detection model iteratively. We enforce the introduced factor of the residual blocks and the scale parameters in Batch Normalization (BN) layers to sparsity to select the less important residual blocks and channels. Moreover, a modified loss function has been proposed to remedy the class-imbalance problem. After removing the unimportant structures iteratively, we get the pruned YOLOv3 trained on our datasets which have more abundant and elaborate classes. Evaluated by our validation sets on the server, the pruned YOLOv3 saves 79.7% floating point operations (FLOPs), 93.8% parameter size, 93.8% model volume and 45.4% inference times with only 4.16% mean of average precision (mAP) loss. Evaluated on the embedded device, the pruned model operates about 13 frames per second with 4.53% mAP loss. These results show that the real-time property and accuracy of the pruned YOLOv3 can meet the needs of the embedded devices in complicated autonomous driving environments.

Downloads

Next from ICPR 2020

SAT-Net: Self-Attention and Temporal Fusion for Facial Action Unit Detection

Similar lecture

On the use of Benford’s law to detect GAN-generated images