Search Results for author:
Found 31 papers, 16 papers with code
Self-Attention Graph Residual Convolutional Networks for Event Detection with dependency relations
While existing GCN-based methods explore latent node-to-node dependency relations according to a stationary adjacency tensor, an attention-based dynamic tensor, which can pay much attention to the key node like event trigger or its neighboring nodes, has not been developed.
Adaptive Caching for Faster Video Generation with Diffusion Transformers
Generating temporally-consistent high-fidelity videos can be computationally expensive, especially over longer temporal spans.
MarDini: Masked Autoregressive Diffusion for Video Generation at Scale
We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework.
Highway Reinforcement Learning
We show, however, that such IS-free methods underestimate the optimal value function (VF), especially for large $n$, restricting their capacity to efficiently utilize information from distant future time steps.
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.
Tune-An-Ellipse: CLIP Has Potential to Find What You Want
Visual prompting of large vision language models such as CLIP exhibits intriguing zero-shot capabilities.
Learning to Identify Critical States for Reinforcement Learning from Videos
Recent work on deep reinforcement learning (DRL) has pointed out that algorithmic information about good policies can be extracted from offline data which lack explicit information about executed actions.
Push the Boundary of SAM: A Pseudo-label Correction Framework for Medical Segmentation
One key advantage of our model is its ability to train deep networks using SAM-generated pseudo labels without relying on a set of expert-level annotations while attaining good segmentation performance.
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.
Mindstorms in Natural Language-Based Societies of Mind
What should be the social structure of an NLSOM?
Open-World Weakly-Supervised Object Localization
To handle such data, we propose a novel paradigm of contrastive representation co-learning using both labeled and unlabeled data to generate a complete G-CAM (Generalized Class Activation Map) for object localization, without the requirement of bounding box annotation.
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.
A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays
Such a point annotation setting can provide weakly instance-level information for abnormality localization with a marginal annotation cost.
Combating Mode Collapse in GANs via Manifold Entropy Estimation
In this paper, we propose a novel training pipeline to address the mode collapse issue of GANs.
Activation Template Matching Loss for Explainable Face Recognition
Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets?
Robust Representation via Dynamic Feature Aggregation
With the regularization and orthogonal classifier, a more compact embedding space can be obtained, which accordingly improves the model robustness against adversarial attacks.
Scene Consistency Representation Learning for Video Scene Segmentation
Additionally, we suggest a more fair and reasonable benchmark to evaluate the performance of Video Scene Segmentation methods.
Why KDAC? A general activation function for knowledge discovery
We hope that KDAC can be exploited as a promising activation function to devote itself to the construction of knowledge.
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.
Manifold-preserved GANs
Generative Adversarial Networks (GANs) have been widely adopted in various fields.
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.
Group-wise Inhibition based Feature Regularization for Robust Classification
The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e. g. corrupted and adversarial samples).
Ranked #40 on
Domain Generalization
on ImageNet-C
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.
