Related papers: High-Quality Pseudo-Label Generation Based on Visu…

LiDAR-based 3D detection has made great progress in recent years. However, the performance of 3D detectors is considerably limited when deployed in unseen environments, owing to the severe domain gap problem. Existing domain adaptive 3D…

High-quality digital terrain models derived from airborne laser scanning (ALS) data are essential for a wide range of geospatial analyses, and their generation typically relies on robust ground filtering (GF) to separate point clouds across…

Weakly supervised Audio-Visual Video Parsing (AVVP) aims to recognize and temporally localize audio, visual, and audio-visual events in videos using only coarse-grained labels. Faced with the challenging task settings, existing research…

Federated learning (FL) enables multiple clients to collaboratively train machine learning models without exposing local data, balancing performance and privacy. However, domain shift and label heterogeneity across clients often hinder the…

Continual test-time adaptation aims to continuously adapt a pre-trained model to a stream of target domain data without accessing source data. Without access to source domain data, the model focuses solely on the feature characteristics of…

Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on…

Feature-level fusion shows promise in collaborative perception (CP) through balanced performance and communication bandwidth trade-off. However, its effectiveness critically relies on input feature quality. The acquisition of high-quality…

Grounded Conversation Generation (GCG) is an emerging vision-language task that requires models to generate natural language responses seamlessly intertwined with corresponding object segmentation masks. Recent models, such as GLaMM and…

Source-free unsupervised domain adaptation (SFUDA) aims to enable the utilization of a pre-trained source model in an unlabeled target domain without access to source data. Self-training is a way to solve SFUDA, where confident target…

This technical report represents the award-winning solution to the Cross-platform 3D Object Detection task in the RoboSense2025 Challenge. Our approach is built upon PVRCNN++, an efficient 3D object detection framework that effectively…

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such…

Test-time adaptation (TTA) aims to adapt a pre-trained model to a new test domain without access to source data after deployment. Existing approaches typically rely on self-training with pseudo-labels since ground-truth cannot be obtained…

Due to the few annotated labels of 3D point clouds, how to learn discriminative features of point clouds to segment object instances is a challenging problem. In this paper, we propose a simple yet effective 3D instance segmentation…

Annotation-efficient segmentation of the numerous mitochondria instances from various electron microscopy (EM) images is highly valuable for biological and neuroscience research. Although unsupervised domain adaptation (UDA) methods can…

Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations. Unlike semi-supervised learning, one cannot select the most…

Conventional object detectors typically operate under a closed-set assumption, limiting recognition to a predefined set of base classes seen during training. Open-vocabulary object detection (OVD) addresses this limitation by leveraging…

Self-driving cars must detect other vehicles and pedestrians in 3D to plan safe routes and avoid collisions. State-of-the-art 3D object detectors, based on deep learning, have shown promising accuracy but are prone to over-fit to domain…

The exploration of Bird's-Eye View (BEV) mapping technology has driven significant innovation in visual perception technology for autonomous driving. BEV mapping models need to be applied to the unlabeled real world, making the study of…

Audio-Visual Source Localization (AVSL) is the task of identifying specific sounding objects in the scene given audio cues. In our work, we focus on semi-supervised AVSL with pseudo-labeling. To address the issues with vanilla hard…

LiDAR and cameras are complementary sensors for 3D object detection in autonomous driving. However, it is challenging to explore the unnatural interaction between point clouds and images, and the critical factor is how to conduct feature…