Related papers: Unified-IoU: For High-Quality Object Detection
In this work, we present a novel method for combining predictions of object detection models: weighted boxes fusion. Our algorithm utilizes confidence scores of all proposed bounding boxes to constructs the averaged boxes. We tested method…
Monocular 3D object detection is an essential task in autonomous driving. However, most current methods consider each 3D object in the scene as an independent training sample, while ignoring their inherent geometric relations, thus…
Unified multimodal models for image generation and understanding represent a significant step toward AGI and have attracted widespread attention from researchers. The main challenge of this task lies in the difficulty in establishing an…
The widespread image applications have greatly promoted the vision-based tasks, in which the Image Quality Assessment (IQA) technique has become an increasingly significant issue. For user enjoyment in multimedia systems, the IQA exploits…
Improving object detectors against occlusion, blur and noise is a critical step to deploy detectors in real applications. Since it is not possible to exhaust all image defects through data collection, many researchers seek to generate hard…
Object detection models, a prominent class of machine learning algorithms, aim to identify and precisely locate objects in images or videos. However, this task might yield uneven performances sometimes caused by the objects sizes and the…
Learning to detect an object in an image from very few training examples - few-shot object detection - is challenging, because the classifier that sees proposal boxes has very little training data. A particularly challenging training regime…
Out-of-distribution (OOD) detection is crucial for the deployment of machine learning models in the open world. While existing OOD detectors are effective in identifying OOD samples that deviate significantly from in-distribution (ID) data,…
We propose Rank & Sort (RS) Loss, a ranking-based loss function to train deep object detection and instance segmentation methods (i.e. visual detectors). RS Loss supervises the classifier, a sub-network of these methods, to rank each…
Specular reflections pose a significant challenge for object segmentation, as their sharp intensity transitions often mislead both conventional algorithms and deep learning based methods. However, as the specular reflection must lie on the…
Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples with numerous high-stake applications including fraud detection and intrusion detection. Due to the lack of ground truth…
Object detection is an essential task for autonomous robots operating in dynamic and changing environments. A robot should be able to detect objects in the presence of sensor noise that can be induced by changing lighting conditions for…
Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a…
Efficient and accurate object detection is an important topic in the development of computer vision systems. With the advent of deep learning techniques, the accuracy of object detection has increased significantly. The project aims to…
Open-world object detection (OWOD) requires incrementally detecting known categories while reliably identifying unknown objects. Existing methods primarily focus on improving unknown recall, yet overlook interpretability, often leading to…
Existing point cloud based 3D detectors are designed for the particular scene, either indoor or outdoor ones. Because of the substantial differences in object distribution and point density within point clouds collected from various…
Precise segmentation of objects with highly similar shapes remains a challenging problem in dense prediction, especially in scenarios with ambiguous boundaries, overlapping instances, and weak inter-instance visual differences. While…
Infrared unmanned aerial vehicle (UAV) images captured using thermal detectors are often affected by temperature dependent low-frequency nonuniformity, which significantly reduces the contrast of the images. Detecting UAV targets under…
Tool wear monitoring is crucial for quality control and cost reduction in manufacturing processes, of which drilling applications are one example. In this paper, we present a U-Net based semantic image segmentation pipeline, deployed on…
The complexity-precision trade-off of an object detector is a critical problem for resource constrained vision tasks. Previous works have emphasized detectors implemented with efficient backbones. The impact on this trade-off of proposal…