Related papers: Weakly Supervised 3D Object Detection from Lidar P…
SSF3D modified the semi-supervised 3D object detection (SS3DOD) framework, which designed specifically for point cloud data. Leveraging the characteristics of non-coincidence and weak correlation of target objects in point cloud, we adopt a…
Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus,…
Semi-supervised object detection (SSOD), leveraging unlabeled data to boost object detectors, has become a hot topic recently. However, existing SSOD approaches mainly focus on horizontal objects, leaving oriented objects common in aerial…
Video salient object detection models trained on pixel-wise dense annotation have achieved excellent performance, yet obtaining pixel-by-pixel annotated datasets is laborious. Several works attempt to use scribble annotations to mitigate…
While there are novel point cloud semantic segmentation schemes that continuously surpass state-of-the-art results, the success of learning an effective model usually rely on the availability of abundant labeled data. However, data…
Improving the detection of distant 3d objects is an important yet challenging task. For camera-based 3D perception, the annotation of 3d bounding relies heavily on LiDAR for accurate depth information. As such, the distance of annotation is…
Advanced Driver-Assistance Systems (ADAS) have successfully integrated learning-based techniques into vehicle perception and decision-making. However, their application in 3D lane detection for effective driving environment perception is…
Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak supervision has been considered in…
Most scanning LiDAR sensors generate a sequence of point clouds in real-time. While conventional 3D object detectors use a set of unordered LiDAR points acquired over a fixed time interval, recent studies have revealed that substantial…
Learning an object detector or retrieval requires a large data set with manual annotations. Such data sets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose to exploit…
Camouflaged Object Detection (COD) demands models to expeditiously and accurately distinguish objects which conceal themselves seamlessly in the environment. Owing to the subtle differences and ambiguous boundaries, COD is not only a…
3D object detection networks tend to be biased towards the data they are trained on. Evaluation on datasets captured in different locations, conditions or sensors than that of the training (source) data results in a drop in model…
3D visual grounding involves finding a target object in a 3D scene that corresponds to a given sentence query. Although many approaches have been proposed and achieved impressive performance, they all require dense object-sentence pair…
Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…
To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common techniques to improve the efficacy of such systems in new…
Three-dimensional (3D) object recognition is crucial for intelligent autonomous agents such as autonomous vehicles and robots alike to operate effectively in unstructured environments. Most state-of-art approaches rely on relatively dense…
Weakly-supervised object detection (WSOD) models attempt to leverage image-level annotations in lieu of accurate but costly-to-obtain object localization labels. This oftentimes leads to substandard object detection and localization at…
Semi-supervised object detection is important for 3D scene understanding because obtaining large-scale 3D bounding box annotations on point clouds is time-consuming and labor-intensive. Existing semi-supervised methods usually employ…
Object discovery is a core task in computer vision. While fast progresses have been made in supervised object detection, its unsupervised counterpart remains largely unexplored. With the growth of data volume, the expensive cost of…
Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, these methods require…