相关论文: FReTAL: Generalizing Deepfake Detection using Know…

Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under…

With diverse presentation forgery methods emerging continually, detecting the authenticity of images has drawn growing attention. Although existing methods have achieved impressive accuracy in training dataset detection, they still perform…

Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage. To reduce the necessity of…

Knowledge distillation (KD) aims at improving the performance of a compact student model by distilling the knowledge from a high-performing teacher model. In this paper, we present an adaptive KD approach, namely AdaDistill, for deep face…

Preventing machine failure is inherently superior to reactive remediation, particularly for critical assets like gas turbines, where early fault detection (FD) is a cornerstone of industrial sustainability. However, modern deep…

Most recent semi-supervised video object segmentation (VOS) methods rely on fine-tuning deep convolutional neural networks online using the given mask of the first frame or predicted masks of subsequent frames. However, the online…

How to learn a universal facial representation that boosts all face analysis tasks? This paper takes one step toward this goal. In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a…

Knowledge distillation (KD) has been widely used to transfer knowledge from large, accurate models (teachers) to smaller, efficient ones (students). Recent methods have explored enforcing consistency by incorporating causal interpretations…

The creation of altered and manipulated faces has become more common due to the improvement of DeepFake generation methods. Simultaneously, we have seen detection models' development for differentiating between a manipulated and original…

Eye tracking (ET) plays a critical role in augmented and virtual reality applications. However, rapidly deploying high-accuracy, on-device gaze estimation for new products remains challenging because hardware configurations (e.g., camera…

Deep learning models for speech rely on large datasets, presenting computational challenges. Yet, performance hinges on training data size. Dataset Distillation (DD) aims to learn a smaller dataset without much performance degradation when…

Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scenarios, it remains the inevitable challenge due to the gap…

Cross-domain few-shot learning (CD-FSL) requires models to generalize from limited labeled samples under significant distribution shifts. While recent methods enhance adaptability through lightweight task-specific modules, they operate…

Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In…

Improving the generalization ability of Deep Neural Networks (DNNs) is critical for their practical uses, which has been a longstanding challenge. Some theoretical studies have uncovered that DNNs have preferences for some frequency…

Knowledge distillation (KD) remains challenging due to the opaque nature of the knowledge transfer process from a Teacher to a Student, making it difficult to address certain issues related to KD. To address this, we proposed UniCAM, a…

RF data-driven device fingerprinting through the use of deep learning has recently surfaced as a possible method for enabling secure device identification and authentication. Traditional approaches are commonly susceptible to the domain…

Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications. However, their accuracy is inadequate in many domains due to distribution shift and overfitting. In…

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the…

Data-Free Knowledge Distillation (DFKD) enables the knowledge transfer from the given pre-trained teacher network to the target student model without access to the real training data. Existing DFKD methods focus primarily on improving image…