Upsampling

About: Upsampling is a research topic. Over the lifetime, 2426 publications have been published within this topic receiving 57613 citations.

Pavement crack detection from CCD images with a locally enhanced transformer network

Abstract: Precisely identifying pavement cracks from charge-coupled devices (CCDs) captured high-resolution images faces many challenges. Even though convolutional neural networks (CNNs) have achieved impressive performance in this task, the stacked convolutional layers fail to extract long-range contextual features and impose high computational costs. Therefore, we propose a locally enhanced Transformer network (LETNet) to completely and efficiently detect pavement cracks. In the LETNet, Transformer is employed to model long-range dependencies. By designing a convolution stem and a local enhancement module, both low-level and high-level local features can be compensated. To take advantage of these rich features, a skip connection strategy and an efficient upsampling module is built to restore detailed information. In addition, a defect rectification module is further developed to reinforce the network for hard sample recognition. The quantitative comparison demonstrates that the proposed LETNet outperformed four advanced deep learning-based models with respect to both efficiency and effectiveness. Specifically, the average precision, recall, ODS, IoU, and frame per second (FPS) of the LETNet on three testing datasets are approximately 93.04%, 92.85%, 92.94%, 94.07%, and 30.80FPS, respectively. We also built a comprehensive pavement crack dataset containing 156 high-resolution manually annotated CCD images and made it publicly available on Zenodo.

Method for analysing media content

Abstract: The invention relates to a method, an apparatus and a computer program product for analyzing media content. The method comprises receiving media content objects by a feature extractor for extracting a plurality of feature maps from said media content objects; processing the plurality of feature maps in a bidirectional Long-Short Term memory neural network, where the bidirectional Long-Short Term memory neural network is aligned along different directions of the feature maps to produce low resolution feature maps; upsampling the low resolution feature maps to the size of received media content; and assigning each pixel of the upsampled feature maps with a label of maximum likelihood for segmenting objects from the upsampled feature maps.

<scp>Canine</scp>: Pre-training an Efficient Tokenization-Free Encoder for Language Representation

Abstract: Pipelined NLP systems have largely been superseded by end-to-end neural modeling, yet nearly all commonly-used models still require an explicit tokenization step. While recent tokenization approaches based on data-derived subword lexicons are less brittle than manually engineered tokenizers, these techniques are not equally suited to all languages, and the use of any fixed vocabulary may limit a model's ability to adapt. In this paper, we present CANINE, a neural encoder that operates directly on character sequences, without explicit tokenization or vocabulary, and a pre-training strategy that operates either directly on characters or optionally uses subwords as a soft inductive bias. To use its finer-grained input effectively and efficiently, CANINE combines downsampling, which reduces the input sequence length, with a deep transformer stack, which encodes context. CANINE outperforms a comparable mBERT model by 2.8 F1 on TyDi QA, a challenging multilingual benchmark, despite having 28% fewer model parameters.

Parallel texture synthesis by upsampling pixel coordinates

Abstract: A method and system for synthesizing texture using upsampled pixel coordinates and a multi-resolution approach. The parallel texture synthesis technique, while based on a neighborhood matching technique having order-independent texture synthesis, extends that approach in at least two areas, including efficient parallel synthesis and intuitive user control. Pixel coordinates are upsampled instead of pixel colors, thereby reducing computational complexity and expense. These upsampled pixel coordinates then are jittered to provide texture variation. The jitter is controllable, such that a user has control over several aspects of the jitter. In addition, each neighborhood-matching pass is split into several sub-passes to improve correction. Using sub-passes improves correction speed and quality. The parallel texture synthesis system and method disclosed herein is designed for implementation on a parallel processor, such as a graphics processing unit.