Related papers: Optimized Deep Encoder-Decoder Methods for Crack S…

Safety-critical infrastructures, such as bridges, are periodically inspected to check for existing damage, such as fatigue cracks and corrosion, and to guarantee the safe use of the infrastructure. Visual inspection is the most frequent…

Surface cracks are a common sight on public infrastructure nowadays. Recent work has been addressing this problem by supporting structural maintenance measures using machine learning methods. Those methods are used to segment surface cracks…

Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications. However, due to the black box nature of deep learning, the best method may fail in some situations. Thus…

The machine learning community has been overwhelmed by a plethora of deep learning based approaches. Many challenging computer vision tasks such as detection, localization, recognition and segmentation of objects in unconstrained…

Semantic segmentation labels are expensive and time consuming to acquire. Hence, pretraining is commonly used to improve the label-efficiency of segmentation models. Typically, the encoder of a segmentation model is pretrained as a…

Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be…

Scene text recognition is a hot research topic in computer vision. Recently, many recognition methods based on the encoder-decoder framework have been proposed, and they can handle scene texts of perspective distortion and curve shape.…

Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to…

Automating the current bridge visual inspection practices using drones and image processing techniques is a prominent way to make these inspections more effective, robust, and less expensive. In this paper, we investigate the development of…

Deep neural networks usually benefit from unsupervised pre-training, e.g. auto-encoders. However, the classifier further needs supervised fine-tuning methods for good discrimination. Besides, due to the limits of full-connection, the…

Encoder-decoder architectures are widely adopted for medical image segmentation tasks. With the lateral skip connection, the models can obtain and fuse both semantic and resolution information in deep layers to achieve more accurate…

We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation. Unlike the conventional model cascade (MC) that is composed of multiple independent models, LC treats a single deep model as a…

Training deep neural networks for 3D segmentation tasks can be challenging, often requiring efficient and effective strategies to improve model performance. In this study, we introduce a novel approach, DeCode, that utilizes label-derived…

The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts…

Semantic segmentation is the task of classifying each pixel in an image. Training a segmentation model achieves best results using annotated images, where each pixel is annotated with the corresponding class. When obtaining fine annotations…

Brain-inspired hyperdimensional computing (HDC) has been recently considered a promising learning approach for resource-constrained devices. However, existing approaches use static encoders that are never updated during the learning…

The recursive intra-frame block partitioning decision process, a crucial component of the next-generation video coding standards, exerts significant influence over the encoding time. In this paper, we propose an encoder-decoder neural…

A physics-informed machine learning framework based on holomorphic neural networks is introduced for detecting cracks in two-dimensional solids from strain or displacement data. Crack detection is formulated as an inverse problem in which…

Foreground segmentation algorithms aim segmenting moving objects from the background in a robust way under various challenging scenarios. Encoder-decoder type deep neural networks that are used in this domain recently perform impressive…

We present a method to segment MRI scans of the human brain into ischemic stroke lesion and normal tissues. We propose a neural network architecture in the form of a standard encoder-decoder where predictions are guided by a spatial…