相关论文: MetaV: A Meta-Verifier Approach to Task-Agnostic M…

Recent advances in Generative Adversarial Networks (GANs) have shown increasing success in generating photorealistic images. But they also raise challenges to visual forensics and model attribution. We present the first study of learning…

Foundation models (FMs) for computer vision learn rich and robust representations, enabling their adaptation to task/domain-specific deployments with little to no fine-tuning. However, we posit that the very same strength can make…

Due to its empirical success in few-shot classification and reinforcement learning, meta-learning has recently received significant interest. Meta-learning methods leverage data from previous tasks to learn a new task in a sample-efficient…

Model fingerprint detection has shown promise to trace the provenance of AI-generated images in forensic applications. However, despite the inherent adversarial nature of these applications, existing evaluations rarely consider adversarial…

In spite of intense research efforts, deep neural networks remain vulnerable to adversarial examples: an input that forces the network to confidently produce incorrect outputs. Adversarial examples are typically generated by an attack…

Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters are updated during meta-update. The normal meta-training…

Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common…

Selecting an appropriate pre-trained source model is a critical, yet computationally expensive, task in transfer learning. Model Transferability Estimation (MTE) methods address this by providing efficient proxy metrics to rank models…

Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans. Different meta-learning approaches all work under/with the mini-batch episodic training framework. Such framework naturally gives the information about…

The vulnerability of deep neural networks to adversarial examples has motivated an increasing number of defense strategies for promoting model robustness. However, the progress is usually hampered by insufficient robustness evaluations. As…

We present MetaUVFS as the first Unsupervised Meta-learning algorithm for Video Few-Shot action recognition. MetaUVFS leverages over 550K unlabeled videos to train a two-stream 2D and 3D CNN architecture via contrastive learning to capture…

Rapid pace of generative models has brought about new threats to visual forensics such as malicious personation and digital copyright infringement, which promotes works on fake image attribution. Existing works on fake image attribution…

Face anti-spoofing (FAS) secures face recognition from presentation attacks (PAs). Existing FAS methods usually supervise PA detectors with handcrafted binary or pixel-wise labels. However, handcrafted labels may are not the most adequate…

We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples. Our framework is motivated by actor-critic reinforcement learning, but can be applied to both reinforcement and supervised learning.…

Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are…

Morphing attacks have diversified significantly over the past years, with new methods based on generative adversarial networks (GANs) and diffusion models posing substantial threats to face recognition systems. Recent research has…

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…

Rapid deployment of new tactile sensors is essential for scalable robotic manipulation, especially in multi-fingered hands equipped with vision-based tactile sensors. However, current methods for inferring contact properties rely heavily on…

Authentication is the task of confirming the matching relationship between a data instance and a given identity. Typical examples of authentication problems include face recognition and person re-identification. Data-driven authentication…

Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectures for anomaly detection, model optimization for a given…