Search Results

Unsupervised source-free domain adaptation methods aim to transfer knowledge acquired from labeled source domain to an unlabeled target domain, where the source data are not accessible during target domain adaptation and it is prohibited to ...

Existing bi-modal salient object detection (SOD) methods primarily rely on fully supervised training strategies that require extensive manual annotation. Undoubtedly, extensive manual annotation is time-consuming and laborious, and the fully ...

• We introduce the semi-supervised learning paradigm to address the bimodal SOD.
• We construct a novel progressive expansion semi-supervised SOD architecture.
• We propose an effective Holistic Multi-scale cross-modal Fusion module.

Low-light is practical in real-life applications and leads to decreased performance of visual perception. For example, the challenges significantly burden the applications of salient object detection (SOD). Existing methods primarily focus on SOD ...

• We construct a new low-light SOD dataset, which consists of 3263 pairs of images.
• We propose a novel low-light SOD model that integrates self-enhancement of saliency.
• Our model performs competitively with fully supervised methods.

Source-free unsupervised domain adaptation aims to adapt a source model to an unlabeled target domain without accessing the source data due to privacy considerations. Existing works mainly solve the problem by self-training methods and ...

• Propose a hierarchical self-supervised learning method for source-free UDA.
• Devise an adaptive pseudo-labeling method to obtain much more reliable labels.
• Improve the pseudo-label quality with hierarchical contrastive learning.

In recommender systems, multi-behavior methods have demonstrated their effectiveness in mitigating issues like data sparsity, a common challenge in traditional single-behavior recommendation approaches. These methods typically infer user preferences from ...

With a focus on abnormal events contained within untrimmed videos, there is increasing interest among researchers in video anomaly detection. Among different video anomaly detection scenarios, weakly-supervised video anomaly detection poses a significant ...

Retrieving useful information from existing collections of oracle bone rubbing images plays a pivotal role in the study of oracle bone inscription decipherment. However, current systems for processing oracle bone information rely on expert-curated ...

The data fusion systems between multiple modals have attracted a wide range of concerns about their adversarial robustness. Recent image captioning attacks lack cross-structure transferability against models with diverse structures. Therefore, ...

• A cross-structure black-box adversarial attack against image caption models.
• A theorem to measure the upper bound of captioning adversarial transferability.
• A weight allocation strategy to enhance adversarial transferability.

Federated Domain Generalization aims to learn a domaininvariant model from multiple decentralized source domains for deployment on unseen target domain. Due to privacy concerns, the data from different source domains are kept isolated, which poses ...

Low-light image enhancement tasks demand an appropriate balance among brightness, color, and illumination. While existing methods often focus on one aspect of the image without considering how to pay attention to this balance, which will cause problems of ...

Existing image restoration models are typically designed for specific tasks and struggle to generalize to out-of-sample degradations not encountered during training. While zero-shot methods can address this limitation by fine-tuning model parameters on ...

Multimodal learning using audio and visual information has improved Violence Detection tasks. However, previous studies overlook the gap between pre-trained networks and the final violence detection task, as well as the semantic inconsistency between ...

• A practical new setting for domain adaptation where source models cannot be transferred to the target domain.
• A domain adaptation framework based on black-box probing that blocks the risk of privacy leakage in practical applications.

Source-free unsupervised domain adaptation is one class of practical deep learning methods which generalize in the target domain without transferring data from source domain. However, existing source-free domain adaptation methods rely on source ...

Blind image deblurring remains challenging due to the ill-posed nature of the traditional blurring function. Although previous supervised methods have achieved great breakthrough with synthetic blurry-sharp image pairs, their generalization ability to ...

Oracle Bone Inscriptions (OBI) are ancient hieroglyphs originated in China and are considered one of the most famous writing systems in the world. Up to now, thousands of OBIs have been discovered, which require deciphering by experts to understand their ...

Most of the existing bi-modal (RGB-D or RGB-T) salient object detection methods attempt to integrate multimodality information through various fusion strategies. However, existing methods lack a clear definition of salient regions before feature fusion, ...

Vision Transformers (ViTs) have been a new paradigm in several computer vision tasks, yet they are susceptible to adversarial examples. Recent studies show it is difficult to transfer adversarial examples generated by ViTs to other models. ...

Unsupervised multi-source domain adaptation aims to obtain a model working well on the unlabeled target domain by reducing the domain gap between the labeled source domains and the unlabeled target domain. Considering the data privacy and storage cost, ...

Due to the low frequency of abnormal behaviors in the real world and the complexity of the definition of abnormal behaviors, anomaly detection in the surveillance video is very challenging. Weakly supervised video anomaly detection has recently ...

Multi-source domain adaptation utilizes multiple source domains to learn the knowledge and transfers it to an unlabeled target domain. To address the problem, most of the existing methods aim to minimize the domain shift by auxiliary distribution ...