Italy

The performance of an audio-visual sound source separation system is determined by its ability to separate audio sources given the images of the sources and the audio mixture. The goal of this study is to investigate the ability to learn the map-ping between the sounds and the images of instruments in the self-supervisied mix-and-seperate training paradigm used by state-of-the-art audio-visual sound source separation methods. Theoretical and empirical analyses illustrate that the self-supervised mix-and-separate training does not automatically learn the 1-to-1 correspondence between visual and audio signals, leading to low audio-visual object classification accuracy. Based on this analysis, a weakly-supervised method called Object-Prior is proposed and evaluated on two audio-visual datasets. The experimental results show that the Object-Prior method outperforms state-of-the-art baselines in the audio-visual sound source separation task. It is also more robust against asynchronized data, where the frame and the audio do not come from the same video, and recognizes musical instruments based on their sound with higher accuracy. This indicates that learning the 1-to-1 correspondence between visual and audio features of an instrument improves the effectiveness of audio-visual sound source separation.

ICPR 2020

Improving Mix-and-Separate Training in Audio-Visual Sound Source Separation with an Object Prior

audio-visual sound source separation

weakly-supervised learning

cross-modal 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

Sound event recognition systems are rapidly becoming part of our life, since they can be profitably used in several vertical markets, ranging from audio security applications to scene classification and multi-modal analysis in social robotics. In the last years, a not negligible part of the scientific community started to apply Convolutional Neural Networks (CNNs) to image-based representations of the audio stream, due to their successful adoption in almost all the computer vision tasks.
In this paper, we carry out a detailed benchmark of various widely used CNN architectures and visual representations on a popular dataset, namely the MIVIA Audio Events database. Our analysis is aimed at understanding how these factors affect the sound event recognition performance with a particular focus on the false positive rate, very relevant in audio surveillance solutions. In fact, although most of the proposed solutions achieve a high recognition rate, the capability of distinguishing the events-of-interest from the background is often not yet sufficient for real systems, and prevent its usage in real applications. Our comprehensive experimental analysis investigates this aspect and allows to identify useful design guidelines for increasing the specificity of sound event recognition systems.

Which are the factors affecting the performance of audio surveillance systems?

Most of the state-of-the-art automatic music transcription (AMT) models break down the main transcription task into sub-tasks such as onset prediction and offset prediction and train them with onset and offset labels. These predictions are then concatenated together and used as the input to train another model with the pitch labels to obtain the final transcription. We attempt to use only the pitch labels (together with spectrogram reconstruction loss) and explore how far this model can go without introducing supervised sub-tasks. In this paper, we do not aim at achieving state-of-the-art transcription accuracy, instead, we explore the effect that spectrogram reconstruction has on our AMT model. Our proposed model consists of two U-nets: the first U-net transcribes the spectrogram into a posteriorgram, and a second U-net transforms the posteriorgram back into a spectrogram. A reconstruction loss is applied between the original spectrogram and the reconstructed spectrogram to constrain the second U-net to focus only on reconstruction. We train our model on three different datasets: MAPS, MAESTRO, and MusicNet. Our experiments show that adding the reconstruction loss can generally improve the note-level transcription accuracy when compared to the same model without the reconstruction part. Moreover, it can also boost the frame-level precision to be higher than the state-of-the-art models. The feature maps learned by our U-net contain gridlike structures (not present in the baseline model) which implies that with the presence of the reconstruction loss, the model is probably trying to count along both the time and frequency axis, resulting in a higher note-level transcription accuracy.

The Effect of Spectrogram Reconstruction on Automatic Music Transcription: An Alternative Approach to Improve Transcription Accuracy

Most deep learning-based image inpainting approaches adopt autoencoder or its variants to ﬁll missing regions in images. Encoders are usually utilized to learn powerful representational spaces, which are important for dealing with sophisticated learning tasks. Speciﬁcally, in image inpainting tasks, masks with any shapes can appear anywhere in images (i.e., free-form masks) which form complex patterns. It is difﬁcult for encoders to capture such powerful representations under this complex situation. To tackle this problem, we propose a self-supervised Siamese inference network to improve the robustness and generalization. It can encode contextual semantics from full-resolution images and obtain more discriminative
representations. we further propose a multi-scale decoder with a novel dual attention fusion module (DAF), which can combine both the restored and known regions in a smooth way. This multi-scale architecture is beneﬁcial for decoding discriminative representations learned by encoders into images layer by layer. In this way, unknown regions will be ﬁlled naturally from outside to inside.

Free-Form Image Inpainting via Contrastive Attention Network

A number of methods based on deep learning have been applied to medical image segmentation and have achieved state-of-the-art performance. Due to the importance of chest x-ray data in studying COVID-19, there is a demand for state-of-the-art models capable of precisely segmenting soft tissue on the chest x-rays. The dataset for exploring the best segmentation model is from Montgomery and Shenzhen hospital which had opened in 2014. The most famous technique is U-Net which has been used for many medical datasets including the Chest X-rays. However, most variant U-Nets mainly focus on the extraction of contextual information and skip connections. There is still a large space for improving the extraction of spatial features. In this paper, we propose a dual encoder fusion U-Net framework for Chest X-rays based on Inception Convolutional Neural Network with dilation, Densely Connected Recurrent Convolutional Neural Network, which is named DEFU-Net. The densely connected recurrent path extends the network deeper for facilitating contextual feature extraction. In order to increase the width of the network and enrich the representation of features, the inception blocks with dilation are adopted. The inception blocks can capture globally and locally spatial information from various receptive fields. At the same time, the two paths are fused by summing features, thus preserving the contextual and spatial information for the decoding part. This multi-learning-scale model is benefiting in the Chest X-ray dataset from two different manufacturers (Montgomery and Shenzhen hospital). The DEFU-Net achieves better performance than basic U-Net, residual U-Net, BCDU-Net, R2U-Net and attention R2U-Net. This model has proved the feasibility for the mixed datasets and approaches state-of-the-art.

Dual Encoder Fusion U-Net (DEFU-Net) for Cross-manufacturer Chest X-ray Segmentation

Representing brain activities by networks is very crucial to understand various cognitive states. This study proposes a novel method to estimate static and dynamic brain networks using Kulback-Leibler divergence. The suggested brain networks are based on the probability distributions of voxel intensity values measured by functional Magnetic Resonance Images (fMRI) recorded while the subjects perform a predefined cognitive task, called complex problem solving. We investigate the validity of the estimated brain networks by modeling and analyzing the different phases of complex problem solving process of human brain, namely planning and execution phases. The suggested computational network model is tested by a classification schema using Support Vector Machines. We observe that the network models can successfully discriminate the planning and execution phases of complex problem solving process with more than 90% accuracy, when the estimated dynamic networks, extracted from the fMRI data, are classified by Support Vector Machines.

Estimating Static and Dynamic Brain Networks by Kulback-Leibler Divergence from fMRI Data

The analysis of axillary and supraclavicular lymph nodes is a primary prognostic factor for the staging of breast cancer. However, due to the size of lymph nodes and the low resolution of PET data, their segmentation is challenging. We investigate the relevance of considering axillary and supraclavicular lymph node segmentation from PET/CT images by coupling Convolutional Neural Networks (CNNs) and Component-Trees (C-Trees). Building upon the U-Net architecture, we propose a framework that couples a multi-modal U-Net fed with PET and CT, coupled with a hierarchical model obtained from the PET that provides additional high-level region-based features as input channels. Our working hypotheses are twofold. First, we take advantage of both anatomical information from CT for detecting the nodes, and functional information from PET for detecting the pathological ones. Second, we consider region-based attributes extracted from C-Tree analysis of 3D PET/CT images to improve the CNN segmentation. We carried out experiments on a dataset of 240 pathological lymph nodes from 52 patients scans, and compared our outputs with human expert-defined ground-truth, leading to promising results.

Segmentation of Axillary and Supraclavicular Tumoral Lymph Nodes in PET/CT: A Hybrid CNN/Component-Tree Approach

Atrial fibrillation is the most common heart rhythm disease. Due to a lack of understanding in matter of underlying atrial structures, current treatments are still not satisfying.Recently, with the popularity of deep learning, many segmentation methods based on fully convolutional networks have been proposed to analyze atrial structures, especially from late gadolinium-enhanced magnetic resonance imaging. However, two problems still occur: 1) segmentation results include the atrial-like background; 2) boundaries are very hard to segment. Most segmentation approaches design a specific network that mainly focuses on the regions, to the detriment of the boundaries.Therefore, this paper proposes an attention full convolutional network framework based on the ResNet-101 architecture, which focuses on boundaries as much as on regions. The additional attention module is added to have the network pay more attention on regions and then to reduce the impact of the misleading similarity of neighboring tissues. We also use a hybrid loss composed of a region loss and a boundary loss to treat boundaries and regions at the same time. We demonstrate the efficiency of the proposed approach on the MICCAI 2018 Atrial Segmentation Challenge public dataset.

Do not Treat Boundaries and Regions Differently: An Example on Heart Left Atrial Segmentation

Recently, substantial progress has been made in the area of Brain-Computer Interface (BCI) using modern machine learning techniques to decode and interpret brain signals. While Electroencephalography (EEG) has provided a non-invasive method of interfacing with a human brain, the acquired data is often heavily subject and session dependent. This makes seamless incorporation of such data into real-world applications intractable as the subject and session data variance can lead to long and tedious calibration requirements and cross-subject generalisation issues. Focusing on a Steady State Visual Evoked Potential (SSVEP) classification systems, we propose a novel means of generating highly-realistic synthetic EEG data invariant to any subject, session or other environmental conditions. Our approach, entitled the Subject Invariant SSVEP Generative Adversarial Network (SIS-GAN), produces synthetic EEG data from multiple SSVEP classes using a single network. Additionally, by taking advantage of a fixed-weight pre-trained subject classification network, we ensure that our generative model remains agnostic to subject-specific features and thus produces subject-invariant data that can be applied to new previously unseen subjects. Our extensive experimental evaluation demonstrates the efficacy of our synthetic data, leading to superior performance, with improvements of up to 16% in zero-calibration classification tasks when trained using our subject-invariant synthetic EEG signals.

Leveraging Synthetic Subject Invariant EEG Signals for Zero Calibration BCI

We propose a new optimization framework for aleatoric uncertainty estimation in regression problems. Existing methods can quantify the error in the target estimation, but they tend to underestimate it. To obtain the predictive uncertainty inherent in an observation, we propose a new separable formulation for the estimation of a signal and of its uncertainty, avoiding the effect of overfitting. By decoupling target estimation and uncertainty estimation, we also control the balance between signal estimation and uncertainty estimation. We conduct three types of experiments: regression with simulation data, age estimation, and depth estimation. We demonstrate that the proposed method outperforms a state-of-the-art technique for signal and uncertainty estimation.

The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals

Although deeper and larger neural networks have achieved better performance, due to overwhelming burden on computation, they cannot meet the demands of deployment on resource-limited devices. An effective strategy to address this problem is to make use of dynamic inference mechanism, which changes the inference path for different samples at runtime. Existing methods only reduce the depth by skipping an entire specific layer, which may lose important information in this layer. In this paper, we propose a novel method called Dynamic Multi-path Neural Network (DMNN), which provides more topology choices in terms of both width and depth on the fly. For better modelling the inference path selection, we further introduce previous state and object category information to guide the training process. Compared to previous dynamic inference techniques, the proposed method is more flexible and easier to incorporate into most modern network architectures. Experimental results on ImageNet and CIFAR-100 demonstrate the superiority of our method on both efficiency and classification accuracy.

Premium content

Downloads

Next from ICPR 2020

Which are the factors affecting the performance of audio surveillance systems?

Similar lecture

Improving Mix-and-Separate Training in Audio-Visual Sound Source Separation with an Object Prior