Related papers: Selective, Regularized, and Calibrated: Harnessing…

Low-rank adaptation (LoRA) has achieved remarkable success in fine-tuning pre-trained vision transformers for various downstream tasks. Existing studies mainly focus on exploring more parameter-efficient strategies or more effective…

Cross-domain few-shot classification task (CD-FSC) combines few-shot classification with the requirement to generalize across domains represented by datasets. This setup faces challenges originating from the limited labeled data in each…

Cross-Domain Few-Shot Semantic Segmentation (CD-FSS) seeks to segment unknown classes in unseen domains using only a few annotated examples. This setting is inherently challenging: source and target domains exhibit substantial distribution…

Robust cross-subject emotion recognition from multimodal physiological signals remains a challenging problem, primarily due to modality heterogeneity and inter-subject distribution shift. To tackle these challenges, we propose a novel…

As bird's-eye-view (BEV) semantic segmentation is simple-to-visualize and easy-to-handle, it has been applied in autonomous driving to provide the surrounding information to downstream tasks. Inferring BEV semantic segmentation conditioned…

Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning.…

The fine-grained localization of clinicians in the operating room (OR) is a key component to design the new generation of OR support systems. Computer vision models for person pixel-based segmentation and body-keypoints detection are needed…

In this paper, we present a new method, Transductive Multi-Head Few-Shot learning (TMHFS), to address the Cross-Domain Few-Shot Learning (CD-FSL) challenge. The TMHFS method extends the Meta-Confidence Transduction (MCT) and Dense…

Generalizing to novel classes unseen during training is a key challenge of few-shot classification. Recent metric-based methods try to address this by local representations. However, they are unable to take full advantage of them due to (i)…

The performance of supervised semantic segmentation methods highly relies on the availability of large-scale training data. To alleviate this dependence, few-shot semantic segmentation (FSS) is introduced to leverage the model trained on…

Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervision which is expensive and time-consuming. Further, training…

Referring image segmentation aims to produce a pixel-level mask for the image region described by a natural-language expression. Although pretrained vision-language models have improved semantic grounding, many existing methods still rely…

Cross-Modality Ship Re-Identification (CMS Re-ID) is critical for achieving all-day and all-weather maritime target tracking, yet it is fundamentally challenged by significant modality discrepancies. Mainstream solutions typically rely on…

Endeavors have been recently made to transfer knowledge from the labeled pinhole image domain to the unlabeled panoramic image domain via Unsupervised Domain Adaptation (UDA). The aim is to tackle the domain gaps caused by the style…

Cache-based approaches stand out as both effective and efficient for adapting vision-language models (VLMs). Nonetheless, the existing cache model overlooks three crucial aspects. 1) Pre-trained VLMs are mainly optimized for image-text…

Learning deep neural networks that are generalizable across different domains remains a challenge due to the problem of domain shift. Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a…

The demand for high-resolution subsurface imaging and continuous Earth monitoring has driven rapid growth in active and passive seismic data from dense geophone deployments, distributed acoustic sensing (DAS) arrays, and large-scale 2D and…

While deep learning has been successfully applied to many real-world computer vision tasks, training robust classifiers usually requires a large amount of well-labeled data. However, the annotation is often expensive and time-consuming.…

Domain generalized semantic segmentation is an essential computer vision task, for which models only leverage source data to learn the capability of generalized semantic segmentation towards the unseen target domains. Previous works…

In recent years, numerous domain adaptive strategies have been proposed to help deep learning models overcome the challenges posed by domain shift. However, even unsupervised domain adaptive strategies still require a large amount of target…