相关论文: A Joint Pixel and Feature Alignment Framework for …

Deep neural networks (DNNs) have achieved remarkable success in radio frequency (RF) fingerprinting for wireless device authentication. However, their practical deployment faces two major limitations: domain shift, where models trained in…

Plankton recognition provides novel possibilities to study various environmental aspects and an interesting real-world context to develop domain adaptation (DA) methods. Different imaging instruments cause domain shift between datasets…

Despite outstanding performance on public benchmarks, face recognition still suffers due to domain mismatch between training (source) and testing (target) data. Furthermore, these domains are not shared classes, which complicates domain…

Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation. Existing feature alignment methods for semantic segmentation learn domain-invariant features by adversarial…

The primary purpose of a fingerprint recognition system is to ensure a reliable and accurate user authentication, but the security of the recognition system itself can be jeopardized by spoof attacks. This study addresses the problem of…

The increasing realism and accessibility of deepfakes have raised critical concerns about media authenticity and information integrity. Despite recent advances, deepfake detection models often struggle to generalize beyond their training…

Object pose estimation enables robots to understand and interact with their environments. Training with synthetic data is necessary in order to adapt to novel situations. Unfortunately, pose estimation under domain shift, i.e., training on…

With the rapid development of mobile devices, smartphones have gradually become an indispensable part of people's lives. Meanwhile, biometric authentication has been corroborated to be an effective method for establishing a person's…

Foundation Vision Encoders have become essential for a wide range of dense vision tasks. However, their low-resolution spatial feature outputs necessitate feature upsampling to produce the high-resolution modalities required for downstream…

Object counting models suffer when deployed across domains with differing density variety, since density shifts are inherently task-relevant and violate standard domain adaptation assumptions. To address this, we propose a theoretical…

Image forgery is a topic that has been studied for many years. Before the breakthrough of deep learning, forged images were detected using handcrafted features that did not require training. These traditional methods failed to perform…

Federated Learning (FL) has emerged as a powerful paradigm for training machine learning models across distributed data sources while preserving data locality. However, the privacy of local data is always a pivotal concern and has received…

Recent advancements in domain generalization for deepfake detection have attracted significant attention, with previous methods often incorporating additional modules to prevent overfitting to domain-specific patterns. However, such…

In this paper, we look at cross-domain few-shot classification which presents the challenging task of learning new classes in previously unseen domains with few labelled examples. Existing methods, though somewhat effective, encounter…

Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend…

Deep learning models often struggle under natural distribution shifts, a common challenge in real-world deployments. Test-Time Adaptation (TTA) addresses this by adapting models during inference without labeled source data. We present the…

While the accuracy of face recognition systems has improved significantly in recent years, the datasets used to train these models are often collected through web crawling without the explicit consent of users, raising ethical and privacy…

Most of existing salient object detection models have achieved great progress by aggregating multi-level features extracted from convolutional neural networks. However, because of the different receptive fields of different convolutional…

Deep-learning-based device fingerprinting has recently been recognized as a key enabler for automated network access authentication. Its robustness to impersonation attacks due to the inherent difficulty of replicating physical features is…

The advancements in the field of AI is increasingly giving rise to various threats. One of the most prominent of them is the synthesis and misuse of Deepfakes. To sustain trust in this digital age, detection and tagging of deepfakes is very…