Related papers: NL-FCOS: Improving FCOS through Non-Local Modules …
One of the greatest challenges for detecting moving objects in the solar system from wide-field survey data is determining whether a signal indicates a true object or is due to some other source, like noise. Object verification has relied…
Object detection is a critical field in computer vision focusing on accurately identifying and locating specific objects in images or videos. Traditional methods for object detection rely on large labeled training datasets for each object…
The state-of-the-art object detection method is complicated with various modules such as backbone, feature fusion neck, RPN and RCNN head, where each module may have different designs and structures. How to leverage the computational cost…
We aim at providing the object detection community with an efficient and performant object detector, termed YOLO-MS. The core design is based on a series of investigations on how multi-branch features of the basic block and convolutions…
Object-based Novelty Detection (ND) aims to identify unknown objects that do not belong to classes seen during training by an object detection model. The task is particularly crucial in real-world applications, as it allows to avoid…
Object detectors are conventionally trained by a weighted sum of classification and localization losses. Recent studies (e.g., predicting IoU with an auxiliary head, Generalized Focal Loss, Rank & Sort Loss) have shown that forcing these…
Recently, promising applications in robotics and augmented reality have attracted considerable attention to 3D object detection from point clouds. In this paper, we present FCAF3D - a first-in-class fully convolutional anchor-free indoor 3D…
In this paper, we aim to improve the performance of a deep learning model towards image classification tasks, proposing a novel anchor-based training methodology, named \textit{Online Anchor-based Training} (OAT). The OAT method, guided by…
Monocular 3D object detection is an important task for autonomous driving considering its advantage of low cost. It is much more challenging than conventional 2D cases due to its inherent ill-posed property, which is mainly reflected in the…
The human visual system contains a hierarchical sequence of modules that take part in visual perception at superordinate, basic, and subordinate categorization levels. During the last decades, various computational models have been proposed…
To achieve human-level dexterity, robots must infer spatial awareness from multimodal sensing to reason over contact interactions. During in-hand manipulation of novel objects, such spatial awareness involves estimating the object's pose…
Detecting fashion landmarks is a fundamental technique for visual clothing analysis. Due to the large variation and non-rigid deformation of clothes, localizing fashion landmarks suffers from large spatial variances across poses, scales,…
The aim of object-centric vision is to construct an explicit representation of the objects in a scene. This representation is obtained via a set of interchangeable modules called \emph{slots} or \emph{object files} that compete for local…
Existing computer vision and object detection methods strongly rely on neural networks and deep learning. This active research area is used for applications such as autonomous driving, aerial photography, protection, and monitoring.…
Human-object interaction detection is an important and relatively new class of visual relationship detection tasks, essential for deeper scene understanding. Most existing approaches decompose the problem into object localization and…
Detecting partially occluded objects is a difficult task. Our experimental results show that deep learning approaches, such as Faster R-CNN, are not robust at object detection under occlusion. Compositional convolutional neural networks…
Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse…
Humans are able to segment images effortlessly without supervision using perceptual grouping. Here, we propose a counter-intuitive computational approach to solving unsupervised perceptual grouping and segmentation: that they arise because…
Few-Shot Object Detection (FSOD) is a rapidly growing field in computer vision. It consists in finding all occurrences of a given set of classes with only a few annotated examples for each class. Numerous methods have been proposed to…
We present Hand-CNN, a novel convolutional network architecture for detecting hand masks and predicting hand orientations in unconstrained images. Hand-CNN extends MaskRCNN with a novel attention mechanism to incorporate contextual cues in…