Related papers: Finetuning Pre-trained Model with Limited Data for…

There is an increasing number of pre-trained deep neural network models. However, it is still unclear how to effectively use these models for a new task. Transfer learning, which aims to transfer knowledge from source tasks to a target…

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…

Current 3D object detection models follow a single dataset-specific training and testing paradigm, which often faces a serious detection accuracy drop when they are directly deployed in another dataset. In this paper, we study the task of…

This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks. In…

With the rise of robotics, LiDAR-based 3D object detection has garnered significant attention in both academia and industry. However, existing datasets and methods predominantly focus on vehicle-mounted platforms, leaving other autonomous…

Domain-Adaptive Pre-training (DAP) has recently gained attention for its effectiveness in fine-tuning pre-trained models. Building on this, continual DAP has been explored to develop pre-trained models capable of incrementally incorporating…

Existing 3D object detection suffers from expensive annotation costs and poor transferability to unknown data due to the domain gap, Unsupervised Domain Adaptation (UDA) aims to generalize detection models trained in labeled source domains…

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.…

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. However, existing methods focus on reducing the domain bias of the detection backbone by inferring a…

Annotating large scale datasets to train modern convolutional neural networks is prohibitively expensive and time-consuming for many real tasks. One alternative is to train the model on labeled synthetic datasets and apply it in the real…

Few-shot learning has made impressive strides in addressing the crucial challenges of recognizing unknown samples from novel classes in target query sets and managing visual shifts between domains. However, existing techniques fall short…

Although current face anti-spoofing methods achieve promising results under intra-dataset testing, they suffer from poor generalization to unseen attacks. Most existing works adopt domain adaptation (DA) or domain generalization (DG)…

Detecting vehicles in aerial imagery is a critical task with applications in traffic monitoring, urban planning, and defense intelligence. Deep learning methods have provided state-of-the-art (SOTA) results for this application. However, a…

The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…

Training an object instance detector where only a few training object images are available is a challenging task. One solution is a cut-and-paste method that generates a training dataset by cutting object areas out of training images and…

Localization and Mapping is an essential component to enable Autonomous Vehicles navigation, and requires an accuracy exceeding that of commercial GPS-based systems. Current odometry and mapping algorithms are able to provide this accurate…

Limited labeled data makes it hard to train models from scratch in medical domain, and an important paradigm is pre-training and then fine-tuning. Large pre-trained models contain rich representations, which can be adapted to downstream…

Recent advances in automotive four-dimensional (4D) Radar have enabled access to raw 4D Radar Tensor (4DRT), offering richer spatial and Doppler information than conventional point clouds. While most existing methods rely on heavily…

Recent advancements in LiDAR-based 3D object detection have significantly accelerated progress toward the realization of fully autonomous driving in real-world environments. Despite achieving high detection performance, most of the…

Accurate reconstruction of static environments from LiDAR scans of scenes containing dynamic objects, which we refer to as Dynamic to Static Translation (DST), is an important area of research in Autonomous Navigation. This problem has been…