Related papers: Beyond First-Order: A Multi-Scale Approach to Fing…
Convolutional neural network (CNN) slides a kernel over the whole image to produce an output map. This kernel scheme reduces the number of parameters with respect to a fully connected neural network (NN). While CNN has proven to be an…
A major factor in the success of deep neural networks is the use of sophisticated architectures rather than the classical multilayer perceptron (MLP). Residual networks (ResNets) stand out among these powerful modern architectures. Previous…
Large-kernel convolutional neural networks (ConvNets) have recently received extensive research attention, but two unresolved and critical issues demand further investigation. 1) The architectures of existing large-kernel ConvNets largely…
The science of fractography revolves around the correlation between topographic characteristics of the fracture surface and the mechanisms and external conditions leading to their creation. While being a topic of investigation for…
Vision-language models are pre-trained by aligning image-text pairs in a common space to deal with open-set visual concepts. To boost the transferability of the pre-trained models, recent works adopt fixed or learnable prompts, i.e.,…
Research on Offline Handwritten Signature Verification explored a large variety of handcrafted feature extractors, ranging from graphology, texture descriptors to interest points. In spite of advancements in the last decades, performance of…
Robots need to exploit high-quality information on grasped objects to interact with the physical environment. Haptic data can therefore be used for supplementing the visual modality. This paper investigates the use of Convolutional Neural…
PET-CT lesion segmentation is challenging due to noise sensitivity, small and variable lesion morphology, and interference from physiological high-metabolic signals. Current mainstream approaches follow the practice of one network solving…
The main focus of this paper is a nonparametric filtering technique for the estimation of interface geometry in bulk materials obtainable from modern imaging measurements. The filtering methodology relies on an assumed hierarchy of…
Optical Coherence Tomography allows ophthalmologist to obtain cross-section imaging of eye retina. Assisted with digital image analysis methods, effective disease detection could be performed. Various methods exist to extract feature from…
Contour detection has been a fundamental component in many image segmentation and object detection systems. Most previous work utilizes low-level features such as texture or saliency to detect contours and then use them as cues for a…
With the development of the convolutional neural network, image style transfer has drawn increasing attention. However, most existing approaches adopt a global feature transformation to transfer style patterns into content images (e.g.,…
Feature pyramid architecture has been broadly adopted in object detection and segmentation to deal with multi-scale problem. However, in this paper we show that the capacity of the architecture has not been fully explored due to the…
The segmentation-free research efforts for addressing handwritten text recognition can be divided into three categories: connectionist temporal classification (CTC), hidden Markov model and encoder-decoder methods. In this paper, inspired…
Fingerprint recognition plays an important role in many commercial applications and is used by millions of people every day, e.g. for unlocking mobile phones. Fingerprint image segmentation is typically the first processing step of most…
To perform unconstrained face recognition robust to variations in illumination, pose and expression, this paper presents a new scheme to extract "Multi-Directional Multi-Level Dual-Cross Patterns" (MDML-DCPs) from face images. Specifically,…
With the rapid development of machine vision technology in recent years, many researchers have begun to focus on feature compression that is better suited for machine vision tasks. The target of feature compression is deep features, which…
Few-shot fine-grained image classification aims to recognize subcategories with high visual similarity using only a limited number of annotated samples. Existing metric learning-based methods typically rely solely on spatial domain…
Few-Shot Class-Incremental Fault Diagnosis (FSC-FD), which aims to continuously learn from new fault classes with only a few samples without forgetting old ones, is critical for real-world industrial systems. However, this challenging task…
Second-order methods have the capability of accelerating optimization by using much richer curvature information than first-order methods. However, most are impractical for deep learning, where the number of training parameters is huge. In…