Related papers: Density Crop-guided Semi-supervised Object Detecti…
Pointly Supervised Object Detection (PSOD) has attracted considerable interests due to its lower labeling cost as compared to box-level supervised object detection. However, the complex scenes, densely packed and dynamic-scale objects in…
Although fully-supervised oriented object detection has made significant progress in multimodal remote sensing image understanding, it comes at the cost of labor-intensive annotation. Recent studies have explored weakly and semi-supervised…
Semi-supervised object detection (SSOD) has made significant progress with the development of pseudo-label-based end-to-end methods. However, many of these methods face challenges due to class imbalance, which hinders the effectiveness of…
Object detection when provided image-level labels instead of instance-level labels (i.e., bounding boxes) during training is an important problem in computer vision, since large scale image datasets with instance-level labels are extremely…
Semi-supervised 3D object detection is a promising yet under-explored direction to reduce data annotation costs, especially for cluttered indoor scenes. A few prior works, such as SESS and 3DIoUMatch, attempt to solve this task by utilizing…
Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly…
Monocular 3D object detection has become a mainstream approach in automatic driving for its easy application. A prominent advantage is that it does not need LiDAR point clouds during the inference. However, most current methods still rely…
Recent aerial object detection models rely on a large amount of labeled training data, which requires unaffordable manual labeling costs in large aerial scenes with dense objects. Active learning effectively reduces the data labeling cost…
In response to the growing demand for 3D object detection in applications such as autonomous driving, robotics, and augmented reality, this work focuses on the evaluation of semi-supervised learning approaches for point cloud data. The…
Few shot segmentation (FSS) aims to learn pixel-level classification of a target object in a query image using only a few annotated support samples. This is challenging as it requires modeling appearance variations of target objects and the…
Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples…
With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection…
Object detection in streaming images is a major step in different detection-based applications, such as object tracking, action recognition, robot navigation, and visual surveillance applications. In mostcases, image quality is noisy and…
I present the Lower Biased Teacher model, an enhancement of the Unbiased Teacher model, specifically tailored for semi-supervised object detection tasks. The primary innovation of this model is the integration of a localization loss into…
Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…
The Mean-Teacher (MT) scheme is widely adopted in semi-supervised object detection (SSOD). In MT, the sparse pseudo labels, offered by the final predictions of the teacher (e.g., after Non Maximum Suppression (NMS) post-processing), are…
A drone monitoring system that integrates deep-learning-based detection and tracking modules is proposed in this work. The biggest challenge in adopting deep learning methods for drone detection is the limited amount of training drone…
Most existing crowd counting systems rely on the availability of the object location annotation which can be expensive to obtain. To reduce the annotation cost, one attractive solution is to leverage a large number of unlabeled images to…
In training object detector based on convolutional neural networks, selection of effective positive examples for training is an important factor. However, when training an anchor-based detectors with sparse annotations on an image, effort…
Deep learning-based video salient object detection has recently achieved great success with its performance significantly outperforming any other unsupervised methods. However, existing data-driven approaches heavily rely on a large…