English
Related papers

Related papers: Improving Sound Event Classification by Increasing…

200 papers

In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding…

Computer Vision and Pattern Recognition · Computer Science 2020-10-12 Hao Zhang , Jianwei Ma

Learning invariant representations from images is one of the hardest challenges facing computer vision. Spatial pooling is widely used to create invariance to spatial shifting, but it is restricted to convolutional models. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2013-03-19 Sainbayar Sukhbaatar , Takaki Makino , Kazuyuki Aihara

We propose a new layer in Convolutional Neural Networks (CNNs) to increase their robustness to several types of noise perturbations of the input images. We call this a push-pull layer and compute its response as the combination of two…

Computer Vision and Pattern Recognition · Computer Science 2019-01-30 Nicola Strisciuglio , Manuel Lopez-Antequera , Nicolai Petkov

State-of-the-art sound event detection (SED) methods usually employ a series of convolutional neural networks (CNNs) to extract useful features from the input audio signal, and then recurrent neural networks (RNNs) to model longer temporal…

Errors in measurements are key to weighting the value of data, but are often neglected in Machine Learning (ML). We show how Convolutional Neural Networks (CNNs) are able to learn about the context and patterns of signal and noise, leading…

Machine Learning · Computer Science 2021-08-11 Natália V. N. Rodrigues , L. Raul Abramo , Nina S. Hirata

Convolutional neural networks are among the most successful architectures in deep learning with this success at least partially attributable to the efficacy of spatial invariance as an inductive bias. Locally connected layers, which differ…

Computer Vision and Pattern Recognition · Computer Science 2020-08-18 Gamaleldin F. Elsayed , Prajit Ramachandran , Jonathon Shlens , Simon Kornblith

Convolution utilizes a shift-equivalent prior of images, thus leading to great success in image processing tasks. However, commonly used poolings in convolutional neural networks (CNNs), such as max-pooling, average-pooling, and…

Computer Vision and Pattern Recognition · Computer Science 2021-09-27 Zhendong Zhang

We conduct an empirical study to test the ability of Convolutional Neural Networks (CNNs) to reduce the effects of nuisance transformations of the input data, such as location, scale and aspect ratio. We isolate factors by adopting a common…

Computer Vision and Pattern Recognition · Computer Science 2016-04-29 Nikolaos Karianakis , Jingming Dong , Stefano Soatto

In some important computer vision domains, such as medical or hyperspectral imaging, we care about the classification of tiny objects in large images. However, most Convolutional Neural Networks (CNNs) for image classification were…

Computer Vision and Pattern Recognition · Computer Science 2020-01-07 Nick Pawlowski , Suvrat Bhooshan , Nicolas Ballas , Francesco Ciompi , Ben Glocker , Michal Drozdzal

Leveraging prior knowledge on intraclass variance due to transformations is a powerful method to improve the sample complexity of deep neural networks. This makes them applicable to practically important use-cases where training data is…

Machine Learning · Computer Science 2022-02-09 Matthias Rath , Alexandru Paul Condurache

Variability in staining protocols, such as different slide preparation techniques, chemicals, and scanner configurations, can result in a diverse set of whole slide images (WSIs). This distribution shift can negatively impact the…

Image and Video Processing · Electrical Eng. & Systems 2023-04-25 Kudaibergen Abutalip , Numan Saeed , Mustaqeem Khan , Abdulmotaleb El Saddik

Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a…

Machine Learning · Computer Science 2018-02-06 Jianbo Ye , Xin Lu , Zhe Lin , James Z. Wang

Access to large corpora with strongly labelled sound events is expensive and difficult in engineering applications. Much research turns to address the problem of how to detect both the types and the timestamps of sound events with weak…

Sound · Computer Science 2021-01-21 Yuzhuo Liu , Hangting Chen , YunWang , Pengyuan Zhang

Singing techniques are used for expressive vocal performances by employing temporal fluctuations of the timbre, the pitch, and other components of the voice. Their classification is a challenging task, because of mainly two factors: 1) the…

Sound · Computer Science 2022-06-27 Yuya Yamamoto , Juhan Nam , Hiroko Terasawa

Learning from set-structured data, such as point clouds, has gained significant attention from the machine learning community. Geometric deep learning provides a blueprint for designing effective set neural networks that preserve the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Abihith Kothapalli , Ashkan Shahbazi , Xinran Liu , Robert Sheng , Soheil Kolouri

Shift invariance is a critical property of CNNs that improves performance on classification. However, we show that invariance to circular shifts can also lead to greater sensitivity to adversarial attacks. We first characterize the margin…

Machine Learning · Computer Science 2021-11-23 Songwei Ge , Vasu Singla , Ronen Basri , David Jacobs

With the introduction of anti-aliased convolutional neural networks (CNN), there has been some resurgence in relooking the way pooling is done in CNNs. The fundamental building block of the anti-aliased CNN has been the application of…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Adithya Sineesh , Mahesh Raveendranatha Panicker

In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity. This feature is universal both within an image and across different images,…

Computer Vision and Pattern Recognition · Computer Science 2018-08-23 Siyu Huang , Xi Li , Zhi-Qi Cheng , Zhongfei Zhang , Alexander Hauptmann

Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…

Sound · Computer Science 2019-07-03 Miquel India , Pooyan Safari , Javier Hernando

Convolutional Neural Networks (CNNs) have achieved remarkable success across a wide range of machine learning tasks by leveraging hierarchical feature learning through deep architectures. However, the large number of layers and millions of…

Machine Learning · Statistics 2025-11-18 Biyi Fang , Truong Vo , Jean Utke , Diego Klabjan