Search Results for author:
Found 16 papers, 9 papers with code
Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
Foundational generative models should be traceable to protect their owners and facilitate safety regulation.
Faster Diffusion via Temporal Attention Decomposition
We explore the role of attention mechanism during inference in text-conditional diffusion models.
Fingerprint Presentation Attack Detector Using Global-Local Model
While by using the texture in-painting-based local module, a local spoofness score predicted from fingerprint patches is obtained.
Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing
In this paper, we propose a domain adversarial attack (DAA) method to mitigate the training instability problem by adding perturbations to the input images, which makes them indistinguishable across domains and enables domain alignment.
The Effect of Antitrust Enforcement on Venture Capital Investments
This paper studies the effect of antitrust enforcement on venture capital (VC) investments and VC-backed companies.
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
As such paired data is time-consuming and labor-intensive to acquire and restricted to a closed set, this potentially becomes the bottleneck for applications in an open world.
Ranked #5 on
Conditional Text-to-Image Synthesis
on COCO-MIG
Dynamically Masked Discriminator for Generative Adversarial Networks
By treating the generated data in training as a stream, we propose to detect whether the discriminator slows down the learning of new knowledge in generated data.
Improving GAN Training via Feature Space Shrinkage
The evaluation results demonstrate that our AdaptiveMix can facilitate the training of GANs and effectively improve the image quality of generated samples.
AdaptiveMix: Improving GAN Training via Feature Space Shrinkage
The evaluation results demonstrate that our AdaptiveMix can facilitate the training of GANs and effectively improve the image quality of generated samples.
NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation
Temporal video segmentation is the get-to-go automatic video analysis, which decomposes a long-form video into smaller components for the following-up understanding tasks.
Decoupled Mixup for Generalized Visual Recognition
Since the observation is that noise-prone regions such as textural and clutter backgrounds are adverse to the generalization ability of CNN models during training, we enhance features from discriminative regions and suppress noise-prone ones when combining an image pair.
A Uniform Representation Learning Method for OCT-based Fingerprint Presentation Attack Detection and Reconstruction
For reconstruction performance, our method achieves the best performance with 0. 834 mIOU and 0. 937 PA. By comparing with the recognition performance on surface 2D fingerprints, the effectiveness of our proposed method on high quality subsurface fingerprint reconstruction is further proved.
FRT-PAD: Effective Presentation Attack Detection Driven by Face Related Task
The proposed method, first introduces task specific features from other face related task, then, we design a Cross-Modal Adapter using a Graph Attention Network (GAT) to re-map such features to adapt to PAD task.
Fingerprint Presentation Attack Detection by Channel-wise Feature Denoising
The proposed method learns important features of fingerprint images by weighing the importance of each channel and identifying discriminative channels and "noise" channels.
Taming Self-Supervised Learning for Presentation Attack Detection: De-Folding and De-Mixing
Even though there are numerous Presentation Attack Detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem.
A Zero-Shot based Fingerprint Presentation Attack Detection System
Therefore, we propose a novel Zero-Shot Presentation Attack Detection Model to guarantee the generalization of the PAD model.
