Related papers: Decoupled and Interactive Regression Modeling for …
Deep learning has driven significant progress in object detection using Synthetic Aperture Radar (SAR) imagery. Existing methods, while achieving promising results, often struggle to effectively integrate local and global information,…
Current face detectors utilize anchors to frame a multi-task learning problem which combines classification and bounding box regression. Effective anchor design and anchor matching strategy enable face detectors to localize faces under…
Despite the importance of unsupervised object detection, to the best of our knowledge, there is no previous work addressing this problem. One main issue, widely known to the community, is that object boundaries derived only from 2D image…
To improve the generalization of detectors, for domain adaptive object detection (DAOD), recent advances mainly explore aligning feature-level distributions between the source and single-target domain, which may neglect the impact of…
In modern electronic manufacturing, defect detection on Printed Circuit Boards (PCBs) plays a critical role in ensuring product yield and maintaining the reliability of downstream assembly processes. However, existing methods often suffer…
Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classification confidence, localization confidence is absent. This…
We present DAFNe, a Dense one-stage Anchor-Free deep Network for oriented object detection. As a one-stage model, it performs bounding box predictions on a dense grid over the input image, being architecturally simpler in design, as well as…
Large-scale well-annotated datasets are of great importance for training an effective object detector. However, obtaining accurate bounding box annotations is laborious and demanding. Unfortunately, the resultant noisy bounding boxes could…
Recent works on two-stage cross-domain detection have widely explored the local feature patterns to achieve more accurate adaptation results. These methods heavily rely on the region proposal mechanisms and ROI-based instance-level features…
The current trend in object detection and localization is to learn predictions with high capacity deep neural networks trained on a very large amount of annotated data and using a high amount of processing power. In this work, we propose a…
Vehicle-Infrastructure Collaborative Perception (VICP) is pivotal for resolving occlusion in autonomous driving, yet the trade-off between communication bandwidth and feature redundancy remains a critical bottleneck. While intermediate…
Single-stage multi-person human pose estimation (MPPE) methods have shown great performance improvements, but existing methods fail to disentangle features by individual instances under crowded scenes. In this paper, we propose a bounding…
Lifelong user behavior sequences are crucial for capturing user interests and predicting user responses in modern recommendation systems. A two-stage paradigm is typically adopted to handle these long sequences: a subset of relevant…
Text in natural images is of arbitrary orientations, requiring detection in terms of oriented bounding boxes. Normally, a multi-oriented text detector often involves two key tasks: 1) text presence detection, which is a classification…
There has been a recent emergence of sampling-based techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or semantic segmentation tasks by simply averaging samples,…
3D object detection based on LiDAR point cloud and prior anchor boxes is a critical technology for autonomous driving environment perception and understanding. Nevertheless, an overlooked practical issue in existing methods is the ambiguity…
Current Point-based detectors can only learn from the provided points, with limited receptive fields and insufficient global learning capabilities for such targets. In this paper, we present a novel Point Dilation Mechanism for single-stage…
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. While effective, existing DA methods suffer from a substantial drop in performance…
Recent advances in neural radiation fields (NeRF) and 3D Gaussian-based SLAM have achieved impressive localization accuracy and high-quality dense mapping in static scenes. However, these methods remain challenged in dynamic environments,…
LiDAR Simultaneous Localization and Mapping (SLAM) systems are essential for enabling precise navigation and environmental reconstruction across various applications. Although current point-to-plane ICP algorithms perform effec- tively in…