Related papers: Automated Model Evaluation for Object Detection vi…

Accurately detecting objects in the environment is a key challenge for autonomous vehicles. However, obtaining annotated data for detection is expensive and time-consuming. We introduce PatchContrast, a novel self-supervised point cloud…

The conventional evaluation protocols on machine learning models rely heavily on a labeled, i.i.d-assumed testing dataset, which is not often present in real world applications. The Automated Model Evaluation (AutoEval) shows an alternative…

Conformal Prediction (CP) is a principled framework for quantifying uncertainty in blackbox learning models, by constructing prediction sets with finite-sample coverage guarantees. Traditional approaches rely on scalar nonconformity scores,…

In this work, we propose a self-improving artificial intelligence system to enhance the safety performance of reinforcement learning (RL)-based autonomous driving (AD) agents using black-box verification methods. RL algorithms have become…

Despite their impressive predictive performance in various computer vision tasks, deep neural networks (DNNs) tend to make overly confident predictions, which hinders their widespread use in safety-critical applications. While there have…

Region proposal algorithms play an important role in most state-of-the-art two-stage object detection networks by hypothesizing object locations in the image. Nonetheless, region proposal algorithms are known to be the bottleneck in most…

Video object detection targets to simultaneously localize the bounding boxes of the objects and identify their classes in a given video. One challenge for video object detection is to consistently detect all objects across the whole video.…

Previous work shows that humans tend to prefer large bounding boxes over small bounding boxes with the same IoU. However, we show here that commonly used object detectors predict large and small boxes equally often. In this work, we…

Predictive models based on machine learning can be highly sensitive to data error. Training data are often combined with a variety of different sources, each susceptible to different types of inconsistencies, and new data streams during…

Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly degrades the performance of SSOD methods. Recent advances…

Confidence-aware learning is proven as an effective solution to prevent networks becoming overconfident. We present a confidence-aware camouflaged object detection framework using dynamic supervision to produce both accurate camouflage map…

Weakly-supervised object detection has recently attracted increasing attention since it only requires image-levelannotations. However, the performance obtained by existingmethods is still far from being satisfactory compared with…

Object detection is an important research area in the field of computer vision. Many detection algorithms have been proposed. However, each object detector relies on specific assumptions of the object appearance and imaging conditions. As a…

The availability of real-world data is a key element for novel developments in the fields of automotive and traffic research. Aerial imagery has the major advantage of recording multiple objects simultaneously and overcomes limitations such…

There has been considerable progress on academic benchmarks for the Reading Comprehension (RC) task with State-of-the-Art models closing the gap with human performance on extractive question answering. Datasets such as SQuAD 2.0 & NQ have…

In many real-world applications involving static environments, the spatial layout of objects remains consistent across instances. However, state-of-the-art object detection models often fail to leverage this spatial prior, resulting in…

The viability of automated driving is heavily dependent on the performance of perception systems to provide real-time accurate and reliable information for robust decision-making and maneuvers. These systems must perform reliably not only…

While substantial progress has been made in the absolute performance of localization and Visual Place Recognition (VPR) techniques, it is becoming increasingly clear from translating these systems into applications that other capabilities…

Detection Transformer (DETR) has redefined object detection by casting it as a set prediction task within an end-to-end framework. Despite its elegance, DETR and its variants still rely on fixed learnable queries and suffer from severe…

Anomaly detection on time series data is increasingly common across various industrial domains that monitor metrics in order to prevent potential accidents and economic losses. However, a scarcity of labeled data and ambiguous definitions…