Related papers: Pseudo-labeling for Scalable 3D Object Detection

Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a significant 70-90% drop in detection rate due to variations in lidar, geography, or weather from their training dataset. This domain gap leads to missing…

Object detection using LiDAR point clouds relies on a large amount of human-annotated samples when training the underlying detectors' deep neural networks. However, generating 3D bounding box annotation for a large-scale dataset could be…

Meta-learning performs adaptation through a limited amount of support set, which may cause a sample bias problem. To solve this problem, transductive meta-learning is getting more and more attention, going beyond the conventional inductive…

Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…

Deep learning is the essential building block of state-of-the-art person detectors in 2D range data. However, only a few annotated datasets are available for training and testing these deep networks, potentially limiting their performance…

LiDAR-based 3D object detection and semantic segmentation are critical tasks in 3D scene understanding. Traditional detection and segmentation methods supervise their models through bounding box labels and semantic mask labels. However,…

Current LiDAR-based 3D object detectors for autonomous driving are almost entirely trained on human-annotated data collected in specific geographical domains with specific sensor setups, making it difficult to adapt to a different domain.…

Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. However, existing approaches are designed in supervised fashion…

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and…

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…

While multi-class 3D detectors are needed in many robotics applications, training them with fully labeled datasets can be expensive in labeling cost. An alternative approach is to have targeted single-class labels on disjoint data samples.…

Foundation models, especially vision-language models (VLMs), offer compelling zero-shot object detection for applications like autonomous driving, a domain where manual labelling is prohibitively expensive. However, their detection latency…

For many practical problems and applications, it is not feasible to create a vast and accurately labeled dataset, which restricts the application of deep learning in many areas. Semi-supervised learning algorithms intend to improve…

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…

Finding correspondences between semantically similar points across images and object instances is one of the everlasting challenges in computer vision. While large pre-trained vision models have recently been demonstrated as effective…

Semantic understanding of 3D point cloud relies on learning models with massively annotated data, which, in many cases, are expensive or difficult to collect. This has led to an emerging research interest in semi-supervised learning (SSL)…

Monocular 3D object detection is an essential perception task for autonomous driving. However, the high reliance on large-scale labeled data make it costly and time-consuming during model optimization. To reduce such over-reliance on human…

We study adapting trained object detectors to unseen domains manifesting significant variations of object appearance, viewpoints and backgrounds. Most current methods align domains by either using image or instance-level feature alignment…

Online mapping models show remarkable results in predicting vectorized maps from multi-view camera images only. However, all existing approaches still rely on ground-truth high-definition maps during training, which are expensive to obtain…

Semi-Supervised Object Detection (SSOD) has achieved resounding success by leveraging unlabeled data to improve detection performance. However, in Open Scene Semi-Supervised Object Detection (O-SSOD), unlabeled data may contains unknown…