Related papers: Boosting Edge Detection with Pixel-wise Feature Se…

The goal of this paper is to present a new efficient image segmentation method based on evolutionary computation which is a model inspired from human behavior. Based on this model, a four layer process for image segmentation is proposed…

We investigate a fundamental aspect of machine vision: the measurement of features, by revisiting clustering, one of the most classic approaches in machine learning and data analysis. Existing visual feature extractors, including ConvNets,…

In computer vision tasks, the ability to focus on relevant regions within an image is crucial for improving model performance, particularly when key features are small, subtle, or spatially dispersed. Convolutional neural networks (CNNs)…

The performance of deep learning based edge detector has far exceeded that of humans, but the huge computational cost and complex training strategy hinder its further development and application. In this paper, we eliminate these…

Establishing a sparse set of keypoint correspon dences between images is a fundamental task in many computer vision pipelines. Often, this translates into a computationally expensive nearest neighbor search, where every keypoint descriptor…

High-dimensional data in many areas such as computer vision and machine learning tasks brings in computational and analytical difficulty. Feature selection which selects a subset from observed features is a widely used approach for…

We introduce the Deep Edge Filter, a novel approach that applies high-pass filtering to deep neural network features to improve model generalizability. Our method is motivated by our hypothesis that neural networks encode task-relevant…

Visual anomaly detection is a highly challenging task, often categorized as a one-class classification and segmentation problem. Recent studies have demonstrated that the student-teacher (S-T) framework effectively addresses this challenge.…

Deep learning based approaches have achieved significant progresses in different tasks like classification, detection, segmentation, and so on. Ensemble learning is widely known to further improve performance by combining multiple…

There has been profound progress in visual saliency thanks to the deep learning architectures, however, there still exist three major challenges that hinder the detection performance for scenes with complex compositions, multiple salient…

In this paper, we present a new image segmentation method based on the concept of sparse subset selection. Starting with an over-segmentation, we adopt local spectral histogram features to encode the visual information of the small segments…

The existing traditional edge detection algorithms process a single pixel on an image at a time, thereby calculating a value which shows the edge magnitude of the pixel and the edge orientation. Most of these existing algorithms convert the…

Edge-preserving smoothing (EPS) can be formulated as minimizing an objective function that consists of data and prior terms. This global EPS approach shows better smoothing performance than a local one that typically has a form of weighted…

Recent feature matching methods have achieved remarkable performance but lack efficiency consideration. In this paper, we revisit the mainstream detector-free matching pipeline and improve all its stages considering both accuracy and…

Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…

Emotion recognition based on EEG (electroencephalography) has been widely used in human-computer interaction, distance education and health care. However, the conventional methods ignore the adjacent and symmetrical characteristics of EEG…

Augmented Reality is an environment-enhancing technology, widely applied in many domains, such as tourism and culture. One of the major challenges in this field is precise detection and extraction of building information through Computer…

Superpixel algorithms aim to over-segment the image by grouping pixels that belong to the same object. Many state-of-the-art superpixel algorithms rely on minimizing objective functions to enforce color ho- mogeneity. The optimization is…

In recent years, great progress has been made in the Lift-Splat-Shot-based (LSS-based) 3D object detection method. However, inaccurate depth estimation remains an important constraint to the accuracy of camera-only and multi-model 3D object…

Machine learning at the edge offers great benefits such as increased privacy and security, low latency, and more autonomy. However, a major challenge is that many devices, in particular edge devices, have very limited memory, weak…