Italy

Detection of moving objects is a critical component of many computer vision tasks. Recently, deep learning architectures have been developed for supervised learning based moving object change detection. Some top performing architectures, like FgSegNet are single frame spatial appearance cue-based detection and tend to overfit to the training videos. We propose a novel compact multi-cue autoencoder deep architecture, Motion U-Net (MU-Net) for robust moving object detection that generalizes much better than FgSegNet and requires nearly 30 times fewer weight parameters. Motion and change cues are estimated using a multi-modal background subtraction module combined with flux tensor motion estimation. MU-Net was trained and evaluated on the CDnet-2014 change detection challenge video sequences and had an overall F-measure of 0.9369. We used the unseen SBI-2015 video dataset to assess generalization capacity where MU-Net had an F-measure of 0.7625 while FgSegNet v2 was 0.3519, less than half the MU-Net accuracy.

ICPR 2020

Motion U-Net: Multi-cue Encoder-Decoder Network for Motion Segmentation

flux tensor

moving object

background subtraction

convolutional neural networks

u-net

change detection

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

In this paper, we propose a deep learning model based on deep multi-view representation learning, to address the video object segmentation task. The proposed model emphasizes the importance of the inherent correlation between video frames and incorporates a multi-view representation learning based on deep canonically correlated autoencoders. The multi-view representation learning in our model provides an efficient mechanism for capturing inherent correlations by jointly extracting useful features and learning better representation into a joint feature space, i.e., shared representation. To increase the training data and the learning capacity, we train the proposed model with pairs of video frames, i.e., Fa and Fb. During the segmentation phase, the deep canonically correlated autoencoders model encodes useful features by processing multiple reference frames together, which is used to detect the frequently reappearing. Our model enhances the state-of-the-art deep learning-based methods that mainly focus on learning discriminative foreground representations over appearance and motion. Experimental results over two large benchmarks demonstrate the ability of the proposed method to outperform competitive approaches and to reach good performances, in terms of semantic segmentation.

Video semantic segmentation using deep multi-view representation learning

In this paper we present a sequential approach to jointly retrieve camera auto-calibration, camera pose and the 3D reconstruction of a non-rigid object from an uncalibrated RGB image sequence, without assuming any prior information about the shape structure, nor the need for a calibration pattern, nor the use of training data at all. To this end, we propose a Bayesian filtering approach based on a sum-of-Gaussians filter composed of a bank of extended Kalman filters (EKF). For every EKF, we make use of dynamic models to estimate its state vector, which later will be Gaussianly combined to achieve a global solution. To deal with deformable objects, we incorporate a mechanical model solved by using the finite element method. Thanks to these ingredients, the resulting method is both efficient and robust to several artifacts such as missing and noisy observations as well as sudden camera motions, while being available for a wide variety of objects and materials, including isometric and elastic shape deformations. Experimental validation is proposed in real experiments, showing its strengths with respect to competing approaches.

Total Estimation from RGB Video: On-line Camera Self-Calibration, Non-Rigid Shape and Motion

Spiking neural network (SNN) is interesting due to its strong bio-plausibility and high energy efficiency. However, its performance is falling far behind conventional deep neural networks (DNNs). In this paper, considering a general class of singlespike temporal-coded integrate-and-fire neurons, we analyze the input-output expressions of both leaky and nonleaky neurons. We show that SNNs built with leaky neurons suffer from the overlynonlinear and overly-complex input-output response, which is the major reason for their difficult training and low performance. This reason is more fundamental than the commonly believed problem of nondifferentiable spikes. To support this claim, we show that SNNs built with nonleaky neurons can have a lesscomplex and less-nonlinear input-output response. They can be easily trained and can have superior performance, which is demonstrated by experimenting with the SNNs over two popular network intrusion detection datasets, i.e., the NSL-KDD and the AWID datasets. Our experiment results show that the proposed SNNs outperform a comprehensive list of DNN models and classic machine learning models. This paper demonstrates that SNNs can be promising and competitive in contrast to common beliefs.

Spiking Neural Networks with Single-Spike Temporal-Coded Neurons for Network Intrusion Detection

Food volume estimation is an essential step in the pipeline of dietary assessment and demands the precise depth estimation of the food surface and table plane. Existing methods based on computer vision require either multi-image input or additional depth maps, reducing convenience of implementation and practical significance. Despite the recent advances in un- supervised depth estimation from a single image, the achieved performance in the case of large texture-less areas needs to be improved. In this paper, we propose a network architecture that jointly performs geometric understanding (i.e., depth prediction and 3D plane estimation) and semantic prediction on a single food image, enabling a robust and accurate food volume estimation regardless of the texture characteristics of the target plane. For the training of the network, only monocular videos with semantic ground truth are required, while the depth map and 3D plane ground truth are no longer needed. Experimental results on two separate food image databases demonstrate that our method performs robustly on texture-less scenarios and is superior to unsupervised networks and structure from motion based approaches, while it achieves comparable performance to fully-supervised methods.

Partially Supervised Multi-Task Network for Single-View Dietary Assessment

In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples. In this context, works have proposed to introduce Graph Neural Networks (GNNs) aiming at exploiting the information contained in other samples treated concurrently, what is commonly referred to as the transductive setting in the literature. These GNNs are trained all together with a backbone feature extractor. In this paper, we propose a new method that relies on graphs only to interpolate feature vectors instead, resulting in a transductive learning setting with no additional parameters to train. Our proposed method thus exploits two levels of information: a) transfer features obtained on generic datasets, b) transductive information obtained from other samples to be classified. Using standard few-shot vision classification datasets, we demonstrate its ability to bring significant gains compared to other works.

Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification

To achieve good performance in face recognition, a large scale training dataset is usually required. A simple yet effective way to improve the recognition performance is to use a dataset as large as possible by combining multiple datasets in the training. However, it is problematic and troublesome to naively combine different datasets due to two major issues. First, the same person can possibly appear in different datasets, leading to an identity overlapping issue between different datasets. Naively treating the same person as different classes in different datasets during training will affect back-propagation and generate non-representative embeddings. On the other hand, manually cleaning labels may take formidable human efforts, especially when there are millions of images and thousands of identities. Second, different datasets are collected in different situations and thus will lead to different domain distributions. Naively combining datasets will make it difficult to learn domain invariant embeddings across different datasets.
In this paper, we propose DAIL: Dataset-Aware and Invariant Learning to resolve the above-mentioned issues. To solve the first issue of identity overlapping, we propose a dataset-aware loss for multi-dataset training by reducing the penalty when the same person appears in multiple datasets. This can be readily achieved with a modified softmax loss with a dataset-aware term. To solve the second issue, domain adaptation with gradient reversal layers is employed for dataset invariant learning. The proposed approach not only achieves the state-of-the-art results on several commonly used face recognition validation sets, including LFW, CFP-FP, and AgeDB-30, but also shows great benefit for practical use.

DAIL: Dataset-Aware and Invariant Learning for Face Recognition


Explainable machine learning has become increasingly prevalent, especially in healthcare where explainable models are vital for ethical and trusted automated decision making. Work on the susceptibility of deep learning models to adversarial attacks has shown the ease of designing samples to mislead a model into making incorrect predictions. In this work, we propose a model agnostic explainability-based method for the accurate detection of adversarial samples on two datasets with different complexity and properties: Electronic Health Record (EHR) and chest X-ray (CXR) data. On the MIMIC-III and Henan-Renmin EHR datasets, we report a detection accuracy of 77% against the Longitudinal Adversarial Attack. On the MIMIC-CXR dataset, we achieve an accuracy of 88%; significantly improving on the state of the art of adversarial detection in both datasets by over 10% in all settings. We propose an anomaly detection based method using explainability techniques to detect adversarial samples which is able to generalise to different attack methods without a need for retraining.

Attack-agnostic Adversarial Detection on Medical Data Using Explainable Machine Learning


In this paper, we propose a novel fusion framework based on a dense network with channel and spatial attention (CSpA-DN) for PET and MR images. In our approach, an encoder composed of the densely connected neural network is constructed to extract features from source images, and a decoder network is leveraged to yield the fused image from these features. Simultaneously, a self-attention mechanism is introduced in the encoder and decoder to further integrate local features along with their global dependencies adaptively. The extracted feature of each spatial position is synthesized by a weighted summation of those features at the same row and column with this position via a spatial attention module. Meanwhile, the interdependent relationship of all feature maps is integrated by a channel attention module. The summation of the outputs of these two attention modules is fed into the decoder and the fused image is generated. Experimental results illustrate the superiorities of our proposed CSpA-DN model compared with state-of-the-art methods in PET and MR images fusion according to both visual perception and objective assessment.

CSpA-DN: Channel and Spatial Attention Dense Network for Fusing PET and MRI Images

Nowadays 360 video analysis has become a significant research topic in the field since the appearance of high-quality and low-cost 360 wearable devices. In this paper, we propose a novel LiteFlowNet360 architecture for 360 videos optical flow estimation. We design LiteFlowNet360 as a domain adaptation framework from perspective video domain to 360 video domain. We adapt it from simple kernel transformation techniques inspired by Kernel Transformer Network (KTN) to cope with inherent distortion in 360 videos caused by the sphere-to-plane projection. First, we apply an incremental transformation of convolution layers in feature pyramid network and show that further transformation in inference and regularization layers are not important, hence reducing the network growth in terms of size and computation cost. Second, we refine the network by training with augmented data in a supervised manner. We perform data augmentation by projecting the images in a sphere and re-projecting to a plane. Third, we train LiteFlowNet360 in a self-supervised manner using target domain 360 videos. Experimental results show the promising results of 360 video optical flow estimation using the proposed novel architecture.

Revisiting Optical Flow Estimation in 360 Videos

In this work, we introduce a new architectural component to Neural Network (NN), i.e., trainable and spectrally initializable matrix transformations on feature maps. While previous literature has already demonstrated the possibility of adding static spectral transformations as feature processors, our focus is on more general trainable transforms. We study the transforms in various architectural configurations on four datasets of different nature: from medical (ColorectalHist, HAM10000) and natural(Flowers) images to historical documents (CB55). With rigorous experiments that control for the number of parameters and randomness, we show that networks utilizing the introduced matrix transformations outperform vanilla neural networks. The observed accuracy increases appreciably across all datasets. In addition, we show that the benefit of spectral initialization leads to significantly faster convergence, as opposed to randomly initialized matrix transformations. The transformations are implemented as auto-differentiable PyTorch modules that can be incorporated into any neural network architecture. The entire code base is open-source.

Downloads

Next from ICPR 2020

Video semantic segmentation using deep multi-view representation learning

Similar lecture

RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery