Related papers: High-Quality Pseudo-Label Generation Based on Visu…
Event-based semantic segmentation has gained popularity due to its capability to deal with scenarios under high-speed motion and extreme lighting conditions, which cannot be addressed by conventional RGB cameras. Since it is hard to…
Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test-time adaptation (CTTA) directly adjusts a pre-trained…
Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliablility of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an…
Multi-subject image generation aims to synthesize images that faithfully preserve the identities of multiple reference subjects while following textual instructions. However, existing methods often suffer from identity inconsistency and…
To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common techniques to improve the efficacy of such systems in new…
Detection of anomalous events in videos is an important problem in applications such as surveillance. Video anomaly detection (VAD) is well-studied in the one-class classification (OCC) and weakly supervised (WS) settings. However, fully…
3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation.…
Semi-supervised action recognition is a challenging but important task due to the high cost of data annotation. A common approach to this problem is to assign unlabeled data with pseudo-labels, which are then used as additional supervision…
Point cloud completion is essential for robotic perception, object reconstruction and supporting downstream tasks like grasp planning, obstacle avoidance, and manipulation. However, incomplete geometry caused by self-occlusion and sensor…
Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…
The application of vision-based multi-view environmental perception system has been increasingly recognized in autonomous driving technology, especially the BEV-based models. Current state-of-the-art solutions primarily encode image…
Recent methods, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have demonstrated remarkable capabilities in novel view synthesis. However, despite their success in producing high-quality images for viewpoints…
Unsupervised domain adaptation for LiDAR-based 3D object detection (3D UDA) based on the teacher-student architecture with pseudo labels has achieved notable improvements in recent years. Although it is quite popular to collect point clouds…
Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated pseudo-labels are…
Detection-free methods typically follow a coarse-to-fine pipeline, extracting image and point cloud features for patch-level matching and refining dense pixel-to-point correspondences. However, differences in feature channel attention…
Source-free object detection (SFOD) aims to adapt a source-trained detector to an unlabeled target domain without access to the labeled source data. Current SFOD methods utilize a threshold-based pseudo-label approach in the adaptation…
Recent works on unsupervised domain adaptation (UDA) focus on the selection of good pseudo-labels as surrogates for the missing labels in the target data. However, source domain bias that deteriorates the pseudo-labels can still exist since…
Unsupervised Domain Adaptation transfers knowledge from a labeled source domain to an unlabeled target domain. Directly deploying Vision-Language Models (VLMs) with prompt tuning in downstream UDA tasks faces the signifi cant challenge of…
Point supervision has become a scalable solution to address dense annotation for infrared small target detection, but its performance is limited by two coupled bottlenecks: unstable pseudo-label evolution in cluttered, low-contrast infrared…
Semantic segmentation of 3D geospatial point clouds is fundamental to remote sensing applications, yet domain shifts caused by regional and acquisition-related variations often degrade model performance. Although domain adaptation can…