Related papers: Faster Training, Fewer Labels: Self-Supervised Pre…
Generating a detailed near-field perceptual model of the environment is an important and challenging problem in both self-driving vehicles and autonomous mobile robotics. A Bird Eye View (BEV) map, providing a panoptic representation, is a…
The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…
High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This paper studies the problem of semi-supervised semantic…
Autonomous vehicle perception systems have traditionally relied on costly LiDAR sensors to generate precise environmental representations. In this paper, we propose a camera-only perception framework that produces Bird's Eye View (BEV) maps…
Deep co-training has recently been proposed as an effective approach for image segmentation when annotated data is scarce. In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent…
A major bottleneck to scaling-up training of self-driving perception systems are the human annotations required for supervision. A promising alternative is to leverage "auto-labelling" offboard perception models that are trained to…
Extracting a Bird's Eye View (BEV) representation from multiple camera images offers a cost-effective, scalable alternative to LIDAR-based solutions in autonomous driving. However, the performance of the existing BEV methods drops…
Semantic segmentation is a crucial task for robot navigation and safety. However, current supervised methods require a large amount of pixelwise annotations to yield accurate results. Labeling is a tedious and time consuming process that…
Self-supervised pre-training for images without labels has recently achieved promising performance in image classification. The success of transformer-based methods, ViT and MAE, draws the community's attention to the design of backbone…
Semi-supervised semantic segmentation aims to utilize limited labeled images and abundant unlabeled images to achieve label-efficient learning, wherein the weak-to-strong consistency regularization framework, popularized by FixMatch, is…
Bird's-eye-view (BEV) representation is crucial for the perception function in autonomous driving tasks. It is difficult to balance the accuracy, efficiency and range of BEV representation. The existing works are restricted to a limited…
We present BEVCon, a simple yet effective contrastive learning framework designed to improve Bird's Eye View (BEV) perception in autonomous driving. BEV perception offers a top-down-view representation of the surrounding environment, making…
As a cornerstone technique for autonomous driving, Bird's Eye View (BEV) segmentation has recently achieved remarkable progress with pinhole cameras. However, it is non-trivial to extend the existing methods to fisheye cameras with severe…
Accurate training labels are a key component for multi-class medical image segmentation. Their annotation is costly and time-consuming because it requires domain expertise. This work aims to develop a dual-branch network and automatically…
This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are…
Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…
Pre-training techniques play a crucial role in deep learning, enhancing models' performance across a variety of tasks. By initially training on large datasets and subsequently fine-tuning on task-specific data, pre-training provides a solid…
Unsupervised image segmentation is a critical task in computer vision. It enables dense scene understanding without human annotations, which is especially valuable in domains where labelled data is scarce. However, existing methods often…
We tackle biomedical image segmentation in the scenario of only a few labeled brain MR images. This is an important and challenging task in medical applications, where manual annotations are time-consuming. Current multi-atlas based…
Expressing images with Multi-Resolution (MR) features has been widely adopted in many computer vision tasks. In this paper, we introduce the MR concept into Bird's-Eye-View (BEV) semantic segmentation for autonomous driving. This…