Italy

We propose insights into feature engineering for musical onset detection, namely about the impact of different window sizes and standardization methods.
Furthermore, we present a universal way of stacking different neural networks to improve the output of a single neural network.

ICPR 2020

Feature Engineering and Stacked Echo State Networks for Musical Onset Detection

reservoir computing

musical onset detection

echo state networks

AIAI 2020 (16th International Conference on Artificial Intelligence Applications and Innovations) should be held in Halkidiki, Greece. Due to current Covid-19 situation the conference will be held virtually. Underline will host a repository of video talks and preserve them for the future. Videos will be released on Underline one day after the conference.

AIAI 2020

poster

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. 


For tree counting tasks, since traditional image processing methods require expensive feature engineering and are not end-to-end frameworks, this will cause additional noise and cannot be optimized overall, so this method has not been widely
used in recent trends of tree counting application. Recently, many deep learning based approaches are designed for this task because of the powerful feature extracting ability. The representative way is bounding box based supervised method, but time-consuming annotations are indispensable for them. Moreover, these methods are difficult to overcome the occlusion or overlap. To solve this problem, we propose a weakly tree counting network (WTCNet) based on deep segmentation network with only point supervision. It can simultaneously complete tree counting with localization and output mask of each tree at the same time. We first adopt
a novel feature extractor network (FENet) to get features of input images, and then an effective strategy is introduced to deal with different mask predictions. In the end, we propose a basic localization guidance accompany with rectification guidance to train the network. We create two different datasets and select an existing challenging plant dataset to evaluate our method on three different tasks. Experimental results show the good performance improvement of our method compared with other existing methods.

Point in: Counting Trees with Weakly Supervised Segmentation Network

Network pruning has become the de facto tool
to accelerate deep neural networks for mobile and edge applications.
Recently, feature-map discriminant based channel
pruning has shown promising results, as it aligns well with the
CNN’s objective of differentiating multiple classes and offers
better interpretability of the pruning decision. However, existing
discriminant-based methods are challenged by computation inefficiency,
as there is a lack of theoretical guidance on quantifying
the feature-map discriminant power. In this paper, we develop a
mathematical formulation to accurately and efficiently quantify
the feature-map discriminativeness, which gives rise to a novel
criterion, Discriminant Information (DI). We analyze the theoretical
property of DI, specifically the non-decreasing property,
that makes DI a valid channel selection criterion. By measuring
the differential discriminant, we can identify and remove those
channels with minimum influence to the discriminant power. The
versatility of DI criterion also enables an intra-layer mixed precision
quantization to further compress the network. Moreover,
we propose a DI-based greedy pruning algorithm and structure
distillation technique to automatically decide the pruned structure
that satisfies certain resource budget, which is a common
requirement in reality. Extensive experiments demonstrate the
effectiveness of our method: our pruned ResNet50 on ImageNet
achieves 44% FLOPs reduction without any Top-1 accuracy loss
compared to unpruned model.

A Discriminant Information Approach to Deep Neural Network Pruning

Edge devices use neural network models learnt on cloud to predict labels of its data records, which may lead to incorrect predictions especially for records that are different from the data involved in the training process, i.e., out-of-distribution (OOD) records. However, recent efforts in OOD detection either require the retraining of the model or assume the existence of a certain amount of OOD records, thus limiting their application in practice.
In this work, we propose a novel OOD detection method (named as NeuralFP) without requiring any access to OOD records, which constructs non-linear fingerprints of neural network models memorizing the information of data observed during training. The key idea of NeuralFP is to exploit the difference in how the neural network model responds to data records in its training set versus data records that are anomalous. Specifically, NeuralFP builds autoencoders for each layer of the neural network model and then carefully analyzes the error distribution of the autocoders in reconstructing the training set to identify OOD records. Through extensive experiments on multiple real-world datasets, we show the effectiveness of NeuralFP in detecting OOD records as well as its advantages over previous approaches. Furthermore, we provide useful guidelines for parameter selection in the practical adoption of NeuralFP.

NeuralFP: Out-of-distribution Detection using Fingerprints of Neural Networks

In this paper, we investigate the potential effect of the adversarially training on the robustness of six advanced deep neural networks against a variety of targeted and nontargeted adversarial attacks. We firstly show that, the ResNet-56 model trained on the 2D representation of the discrete wavelet transform appended with the tonnetz chromagram outperforms other models in terms of recognition accuracy. Then we demonstrate the positive impact of adversarially training on this model
as well as other deep architectures against six types of attack algorithms (white and black-box) with the cost of the reduced recognition accuracy and limited adversarial perturbation. We run our experiments on two benchmarking environmental sound
datasets and show that without any imposed limitations on the budget allocations for the adversary, the fooling rate of the adversarially trained models can exceed 90%. In other words, adversarial attacks exist in any scales, but they might require
higher adversarial perturbations compared to non-adversarially trained models

Adversarially Training for Audio Classifiers

Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low amplitude perturbations, barely perceptible by the human eye, can lead to a drastic reduction in labelling performance. This article proposes a new context module, called Transformer- Encoder Detector Module, that can be applied to an object detector to (i) improve the labelling of object instances; and (ii) improve the detector’s robustness to adversarial attacks. The proposed model achieves higher mAP, F1 scores and AUC average score of up to 13% compared to the baseline Faster-RCNN detector, and an mAP score 8 points higher on images subjected to FFF or UAP attacks due to the inclusion of both contextual and visual features extracted from scene and encoded into the model. The result demonstrates that a simple ad-hoc context module can improve the reliability of object detectors significantly.

Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection

Long-term visual tracking is a challenging problem.
State-of-the-art long-term trackers, e.g., GlobalTrack,
utilize region proposal networks (RPNs) to generate target
proposals. However, the performance of the trackers is
affected by occlusions and large scale or ratio variations.
To address these issues, in this paper, we are the first to
propose a novel architecture with transformers for
long-term visual tracking. Specifically, the proposed
Visual Tracking Transformer (VTT) utilizes a transformer
encoder-decoder architecture for aggregating global
information to deal with occlusion and large scale or ratio
variation. Furthermore, it also shows better discriminative
power against instance-level distractors without the need
for extra labeling and hard-sample mining. We conduct
extensive experiments on three largest long-term tracking
dataset and have achieved state-of-the-art performance.

VTT: Long-term Visual Tracking with Transformers

Despite their tremendous success in modelling high-dimensional data manifolds, deep neural networks suffer from the threat of adversarial attacks - Existence of perceptually valid input-like samples obtained through careful perturbation that lead to degradation in the performance of the underlying model. Major concerns with existing defense mechanisms includenon-generalizability across different attacks, models and largeinference time. In this paper, we propose a generalized defense mechanism capitalizing on the expressive power of regularized latent space based generative models. We design an adversarial filter, devoid of access to classifier and adversaries, which makes it usable in tandem with any classifier. The basic idea is to learn a Lipschitz constrained mapping from the data manifold, incorporating adversarial perturbations, to a quantized latent space and re-map it to the true data manifold. Specifically, wesimultaneously auto-encode the data manifold and its pertur-bations implicitly through the perturbations of the regularizedand quantized generative latent space, realized using variationalinference. We demonstrate the efficacy of the proposed formula-tion in providing resilience against multiple attack types (blackand white box) and methods, while being almost real-time. Ourexperiments show that the proposed method surpasses the state-of-the-art techniques in several cases. The implementation codeis available at - https://github.com/mayank31398/lqvae.

Variational Inference with Latent Space Quantization for Adversarial Resilience


We introduce an adaptive L2 regularization mechanism in the setting of person re-identification. In the literature, it is common practice to utilize hand-picked regularization factors which remain constant throughout the training procedure. Unlike existing approaches, the regularization factors in our proposed method are updated adaptively through backpropagation. This is achieved by incorporating trainable scalar variables as the regularization factors, which are further fed into a scaled hard sigmoid function. Extensive experiments on the Market-1501, DukeMTMC-reID and MSMT17 datasets validate the effectiveness of our framework. Most notably, we obtain state-of-the-art performance on MSMT17, which is the largest dataset for person re-identification. Source code is publicly available at https://github.com/nixingyang/AdaptiveL2Regularization.

Adaptive L2 Regularization in Person Re-Identification


In zero-shot cross-lingual transfer, a supervised NLP task trained on a corpus in one language is directly applicable to another language without any additional training. A source of cross-lingual transfer can be as straightforward as lexical overlap between languages (e.g., use of the same scripts, shared subwords) that naturally forces text embeddings to occupy a similar representation space. Recently introduced cross-lingual language model (XLM) pretraining brings out neural parameter sharing in Transformer-style networks as the most important factor for the transfer. In this paper, we aim to validate the hypothetically strong cross-lingual transfer properties induced by XLM pretraining. Particularly, we take XLM-RoBERTa (XLMR) in our experiments that extend semantic textual similarity (STS), SQuAD and KorQuAD for machine reading comprehension, sentiment analysis, and alignment of sentence embeddings under various cross-lingual settings. Our results indicate that the presence of cross-lingual transfer is most pronounced in STS, sentiment analysis the next, and MRC the last. That is, the complexity of a downstream task softens the degree of cross-lingual transfer. All of our results are empirically observed and
measured, and we make our code and data publicly available.

Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks

We propose a framework to analyze vehicles behavior within shared road segments like intersections or at narrow passages. 
The system first identifies critical interaction regions based on topological knowledge. 
It then checks possible colliding trajectories from the current state of vehicles in the scene, defined by overlapping occupation times in road segments. 
The interaction between vehicles is analyzed over a short time horizon based on an initial action from one vehicle and the reaction by the other. 
The observed reaction is classified by attention and the collaboration of the opponent vehicle, whether it helps to resolve the situation or hinders it.
The output is a classification of behavior terms of active participation in the interaction and driving style in terms of collaborative or disruptive behavior.

Premium content

Feature Engineering and Stacked Echo State Networks for Musical Onset Detection

Downloads

Next from ICPR 2020

Point in: Counting Trees with Weakly Supervised Segmentation Network

Similar lecture

Deep Echo State Networks in Industrial Applications