Related papers: Harnessing Uncertainty-aware Bounding Boxes for Un…

Deep learning has led to great progress in the detection of mobile (i.e. movement-capable) objects in urban driving scenes in recent years. Supervised approaches typically require the annotation of large training sets; there has thus been…

The proliferation of Deep Neural Networks has resulted in machine learning systems becoming increasingly more present in various real-world applications. Consequently, there is a growing demand for highly reliable models in many domains,…

We present a Deep Cuboid Detector which takes a consumer-quality RGB image of a cluttered scene and localizes all 3D cuboids (box-like objects). Contrary to classical approaches which fit a 3D model from low-level cues like corners, edges,…

This paper addresses unsupervised discovery and localization of dominant objects from a noisy image collection with multiple object classes. The setting of this problem is fully unsupervised, without even image-level annotations or any…

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…

Autonomous Vehicles (AVs) use natural images and videos as input to understand the real world by overlaying and inferring digital elements, facilitating proactive detection in an effort to assure safety. A crucial aspect of this process is…

Ensuring robust 3D object detection and localization is crucial for many applications in robotics and autonomous driving. Recent models, however, face difficulties in maintaining high performance when applied to domains with differing…

We present an endpoint box regression module(epBRM), which is designed for predicting precise 3D bounding boxes using raw LiDAR 3D point clouds. The proposed epBRM is built with sequence of small networks and is computationally lightweight.…

Self-training for unsupervised domain adaptive object detection is a challenging task, of which the performance depends heavily on the quality of pseudo boxes. Despite the promising results, prior works have largely overlooked the…

We study how state-of-the-art neural networks for 3D object detection using a single-stage pipeline can be made safety aware. We start with the safety specification (reflecting the capability of other components) that partitions the 3D…

Unsupervised Domain Adaptation (UDA) technique has been explored in 3D cross-domain tasks recently. Though preliminary progress has been made, the performance gap between the UDA-based 3D model and the supervised one trained with fully…

Existing LiDAR-Camera fusion methods have achieved strong results in 3D object detection. To address the sparsity of point clouds, previous approaches typically construct spatial pseudo point clouds via depth completion as auxiliary input…

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD…

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…

Passive methods for object detection and segmentation treat images of the same scene as individual samples and do not exploit object permanence across multiple views. Generalization to novel or difficult viewpoints thus requires additional…

Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates, which are extremely expensive to acquire. Noisy annotations are much more easily accessible, but…

Existing 3D object detectors encounter extreme challenges in localizing unseen 3D objects and recognizing them as unseen, which is a crucial technology in autonomous driving in the wild. To address these challenges, we propose practical…

Semi-supervised Learning (SSL) has received increasing attention in autonomous driving to reduce the enormous burden of 3D annotation. In this paper, we propose UpCycling, a novel SSL framework for 3D object detection with zero additional…

Without manually annotated identities, unsupervised multi-object trackers are inferior to learning reliable feature embeddings. It causes the similarity-based inter-frame association stage also be error-prone, where an uncertainty problem…

Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in…