Search Results for author:
Found 13 papers, 8 papers with code
Discovering Transferable Forensic Features for CNN-generated Images Detection
Visual counterfeits are increasingly causing an existential conundrum in mainstream media with rapid evolution in neural image synthesis methods.
Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?
Critically, there is no effort to understand and resolve these contradictory findings, leaving the primal question -- to smooth or not to smooth a teacher network?
To Smooth or not to Smooth? On Compatibility between Label Smoothing and Knowledge Distillation
On the contrary, Shen et al. [2] claim that LS enlarges the distance between semantically similar classes; therefore a LS-trained teacher is compatible with KD.
A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection
Our results prompt re-thinking of using high frequency Fourier spectrum decay attributes for CNN-generated image detection.
InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning
While Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues.
On Data Augmentation for GAN Training
We provide theoretical analysis to show that using our proposed DAG aligns with the original GAN in minimizing the Jensen-Shannon (JS) divergence between the original distribution and model distribution.
Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game
From the analysis, we identify issues of SS tasks which allow a severely mode-collapsed generator to excel the SS tasks.
Ranked #4 on
Image Generation
on ImageNet 32x32
3D Face Pose and Animation Tracking via Eigen-Decomposition based Bayesian Approach
This paper presents a new method to track both the face pose and the face animation with a monocular camera.
An Improved Self-supervised GAN via Adversarial Training
Importantly, we find out that simultaneously training the discriminator to classify the fake class from the pseudo-classes of real samples for the classification task will improve the discriminator and subsequently lead better guides to train generator.
Improving GAN with neighbors embedding and gradient matching
Second, we propose a new technique, gradient matching, to align the distributions of the generated samples and the real samples.
DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN
To the best of our knowledge, our method is the first data augmentation technique focused on improving performance in unsupervised anomaly detection.
Dist-GAN: An Improved GAN using Distance Constraints
We use this constraint to explicitly prevent the generator from mode collapse.
Ranked #18 on
Image Generation
on STL-10
On-device Scalable Image-based Localization via Prioritized Cascade Search and Fast One-Many RANSAC
In order to overcome the resource constraints of mobile devices, we propose a system design that leverages the scalability advantage of image retrieval and accuracy of 3D model-based localization.
