Italy


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.

ICPR 2020

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

music information retrieval

audio signal processing

automatic music transcription

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. 


technical paper

Identifying vehicles across a network of cameras with non-overlapping fields of view remains a challenging research problem due to scene occlusions, significant inter-class similarity and intra-class variability. In this work, we propose an end-to-end multi-level re-identification network that is capable of successfully projecting same identity vehicles closer to one another in the embedding space, compared to vehicles of different identities. Robust feature representations are obtained by combining features at multiple levels of the network. As for the learning process, we employ a recent state-of-the-art structured metric learning loss function previously applied to other retrieval problems and adjust it to the vehicle re-identification task. Furthermore, we explore the cases of image-to-image, image-to video and video-to-video similarity metric. Finally, we evaluate our system and achieve great performance on two large-scale publicly available datasets. Compared to most existing state-of-art approaches, our approach is simpler and more straightforward, utilizing only identity-level annotations, while avoiding post-processing the ranking results (re-ranking) at the testing phase.

Multi-level Deep Learning Vehicle Re-identification using Ranked-based Loss Functions

In this work, loop-closure detection from LiDAR scans is defined as an image re-identification problem. Re-identification is performed by computing Euclidean distances of a query scan to a gallery set of previous scans. The distances are computed in a feature embedding space where the scans are mapped by a convolutional neural network (CNN). The network is trained using the triplet loss training strategy. In our experiments we compare different backbone networks,
variants of the triplet loss and generic and LiDAR specific data augmentation techniques. With a realistic indoor dataset the best architecture obtains the mean average precision (mAP) above 0.94.

Loop-closure detection by LiDAR scan re-identification

Stochastic Label Refinery is a simple method to generate better soft label and improve the model performance.

Stochastic Label Refinery: Toward Better Target Label Distribution


Fluorescein Angiography (FA) is a technique that employs the designated camera for Fundus photography incorporating excitation and barrier filters. FA also requires fluorescein dye that is injected intravenously, which might cause adverse effects ranging from nausea, vomiting to even fatal anaphylaxis. Currently, no other fast and non-invasive technique exists that can generate FA without coupling with Fundus photography. To eradicate the need for an invasive FA extraction procedure, we introduce an Attention-based Generative network that can synthesize Fluorescein Angiography from Fundus images. The proposed gan incorporates multiple attention based skip connections in generators and comprises novel residual blocks for both generators and discriminators. It utilizes reconstruction, feature-matching, and perceptual loss along with adversarial training to produces realistic Angiograms that is hard for experts to distinguish from real ones. Our experiments confirm that the proposed architecture surpasses recent state-of-the-art generative networks for fundus-to-angio translation task.

Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks


This paper studies the problem of Person Re-Identification (ReID)
for large-scale applications. Recent research efforts have been devoted
to building complicated part models, which introduce considerably
high computational cost and memory consumption, inhibiting its practicability
in large-scale applications. This paper aims to develop a novel learning
strategy to find efficient feature embeddings while maintaining the
balance of accuracy and model complexity. More specifically, we find
by enhancing the classical triplet loss together with cross-entropy
loss, our method can explore the hard examples and build a discriminant
feature embedding yet compact enough for large-scale applications.
Our method is carried out progressively using Bayesian optimization,
and we call it the Progressive Learning Algorithm (PLA). Extensive
experiments on three large-scale datasets show that our PLA is comparable
or better than the state-of-the-arts. Especially, on the challenging
Market-1501 dataset, we achieve Rank-1=94.7%/mAP=89.4% while saving
at least 30\% parameters than strong part models.

TAAN: Task-Aware Attention Network for Few-shot Classification


Audio-visual co-segmentation is a task to extract segments and regions corresponding to specific events on unlabeled audio and video signals. It is particularly important to accomplish it in an unsupervised way, since it is generally very difficult to manually label all the objects and events appearing in audio-visual signals for supervised learning. Here, we propose to take advantage of the temporal proximity of corresponding audio and video entities included in the signals. For this purpose, we newly employ a guided attention scheme to this task to efficiently detect and utilize temporal co-occurrences of audio and video information. Experiments using a real TV broadcasts of sumo wrestling, a sport event, with live commentaries show that our model can automatically extract specific athlete movements and its spoken descriptions in an unsupervised manner.

Unsupervised Co-Segmentation for Athlete Movements and Live Commentaries Using Crossmodal Temporal Proximity

Kernel-based LIME with Feature Dependency Sampling

Activation functions and attention mechanisms are typically treated as having different purposes and have evolved differently.
However, both concepts can be formulated as a non-linear gating function. 
Inspired by their similarity, we propose a novel type of activation units called attentional activation (ATAC) units as a unification of activation functions and attention mechanisms.
In particular, we propose a local channel attention module for the simultaneous non-linear activation and element-wise feature refinement, which locally aggregates point-wise cross-channel feature contexts.
By replacing the well-known rectified linear units by 
such ATAC units in convolutional networks, we can construct fully attentional networks that perform significantly better with a modest number of additional parameters.
We conducted detailed ablation studies on the ATAC units using several host networks with varying network depths to empirically verify the effectiveness and efficiency of the units.
Furthermore, we compared the performance of the ATAC units against existing activation functions as well as other attention mechanisms on the CIFAR-10, CIFAR-100, and ImageNet datasets.
Our experimental results show that networks constructed with the proposed ATAC units generally yield performance gains over their competitors given a comparable number of parameters.

Attention as Activation

Evaluation of generative AI is a difficult problem, especially in artistic domains in which aesthetic qualities of generated samples are to an extent subjective, such as in music. The most widely accepted method for evaluating such models is to conduct a survey of users, which is a resource intensive process. In this work we propose a framework for cheaply evaluating generative models in the symbolic music domain by utilizing tools from music theory, such as the circle of fifths, with the goal of producing quantifiable metrics which reflect the "musicality" of a written score or MIDI file.

Heuristics for Evaluation of AI Generated Music

Despite the success of deep neural networks (DNN) in many applications, their ability to model uncertainty is still significantly limited. For example, in safety-critical applications such as autonomous driving, it is crucial to obtain a prediction that reflects different types of uncertainty to address life-threatening situations appropriately. In such cases, it is essential to be aware of the risk (i.e.,~aleatoric uncertainty) and the reliability (i.e.,~epistemic uncertainty) that comes with a prediction. We present AE-DNN, a model allowing the separation of aleatoric and epistemic uncertainty while maintaining a proper generalization capability. AE-DNN is based on deterministic DNN, which can determine the respective uncertainty measures in a single forward pass. In analyses with synthetic and image data, we show that our method improves the modeling of epistemic uncertainty while providing an intuitively understandable separation of risk and reliability.

Premium content

Downloads

Next from ICPR 2020

Multi-level Deep Learning Vehicle Re-identification using Ranked-based Loss Functions

Similar lecture

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