Related papers: Mx2M: Masked Cross-Modality Modeling in Domain Ada…

Cross-domain visual data matching is one of the fundamental problems in many real-world vision tasks, e.g., matching persons across ID photos and surveillance videos. Conventional approaches to this problem usually involves two steps: i)…

Multi-modal magnetic resonance imaging (MRI) provides information of lesions for computer-aided diagnosis from different views. Deep learning algorithms are suitable for identifying specific anatomical structures, segmenting lesions, and…

Segment Anything Models (SAMs), as vision foundation models, have demonstrated remarkable performance across various image analysis tasks. Despite their strong generalization capabilities, SAMs encounter challenges in fine-grained detail…

Domain adaptation for semantic segmentation aims to improve the model performance in the presence of a distribution shift between source and target domain. Leveraging the supervision from auxiliary tasks~(such as depth estimation) has the…

Covariate shifts are a common problem in predictive modeling on real-world problems. This paper proposes addressing the covariate shift problem by minimizing Maximum Mean Discrepancy (MMD) statistics between the training and test sets in…

Vision foundation models like DINOv2 demonstrate remarkable potential in medical imaging despite their origin in natural image domains. However, their design inherently works best for uni-modal image analysis, limiting their effectiveness…

Vision-language retrieval is an important multi-modal learning topic, where the goal is to retrieve the most relevant visual candidate for a given text query. Recently, pre-trained models, e.g., CLIP, show great potential on retrieval…

We introduce Multi-Source 3D (MS3D), a new self-training pipeline for unsupervised domain adaptation in 3D object detection. Despite the remarkable accuracy of 3D detectors, they often overfit to specific domain biases, leading to…

Cross-domain Recommendation systems leverage multi-domain user interactions to improve performance, especially in sparse data or new user scenarios. However, CDR faces challenges such as effectively capturing user preferences and avoiding…

Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique. The existing MIM methods adopt the strategy to mask random patches of the image and reconstruct the…

Deep-learning models for 3D point cloud semantic segmentation exhibit limited generalization capabilities when trained and tested on data captured with different sensors or in varying environments due to domain shift. Domain adaptation…

Recent developments in the unsupervised domain adaptation (UDA) enable the unsupervised machine learning (ML) prediction for target data, thus this will accelerate real world applications with ML models such as image recognition tasks in…

Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning methods require large amounts of labeled data for training. Manual annotation is expensive, while simulators can…

Multi-view cooperative perception and multimodal fusion are essential for reliable 3D spatiotemporal understanding in autonomous driving, especially under occlusions, limited viewpoints, and communication delays in V2X scenarios. This paper…

In real-world applications, speaker recognition models often face various domain-mismatch challenges, leading to a significant drop in performance. Although numerous domain adaptation techniques have been developed to address this issue,…

Object discovery, which refers to the task of localizing objects without human annotations, has gained significant attention in 2D image analysis. However, despite this growing interest, it remains under-explored in 3D data, where…

Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi-modal extension of test-time adaptation for…

3D semantic segmentation plays a pivotal role in autonomous driving and road infrastructure analysis, yet state-of-the-art 3D models are prone to severe domain shift when deployed across different datasets. In this paper, we propose an…

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes…

Any novel medical imaging modality that differs from previous protocols e.g. in the number of imaging channels, introduces a new domain that is heterogeneous from previous ones. This common medical imaging scenario is rarely considered in…