37 citations · 69 across the 19 of their papers we have counts for
19 papers
Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
Haozhe Liu, Wentian Zhang, Bing Li +2
Foundational generative models should be traceable to protect their owners and facilitate safety regulation. To achieve this, traditional approaches embed identifiers based on supe…
Faster Diffusion via Temporal Attention Decomposition
Haozhe Liu, Wentian Zhang, Jinheng Xie +6
We explore the role of attention mechanism during inference in text-conditional diffusion models. Empirical observations suggest that cross-attention outputs converge to a fixed po…
Fingerprint Presentation Attack Detector Using Global-Local Model
Haozhe Liu, Wentian Zhang, Feng Liu +2
The vulnerability of automated fingerprint recognition systems (AFRSs) to presentation attacks (PAs) promotes the vigorous development of PA detection (PAD) technology. However, PA…
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
Jinheng Xie, Yuexiang Li, Yawen Huang +4
Recent text-to-image diffusion models have demonstrated an astonishing capacity to generate high-quality images. However, researchers mainly studied the way of synthesizing images…
Learning to Identify Critical States for Reinforcement Learning from Videos
Haozhe Liu, Mingchen Zhuge, Bing Li +4
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…
Dynamically Masked Discriminator for Generative Adversarial Networks
Wentian Zhang, Haozhe Liu, Bing Li +5
Training Generative Adversarial Networks (GANs) remains a challenging problem. The discriminator trains the generator by learning the distribution of real/generated data. However,…
Mindstorms in Natural Language-Based Societies of Mind
Mingchen Zhuge, Haozhe Liu, Francesco Faccio +23
Both Minsky's "society of mind" and Schmidhuber's "learning to think" inspire diverse societies of large multimodal neural networks (NNs) that solve problems by interviewing each o…
Open-World Weakly-Supervised Object Localization
Jinheng Xie, Zhaochuan Luo, Yuexiang Li +3
While remarkable success has been achieved in weakly-supervised object localization (WSOL), current frameworks are not capable of locating objects of novel categories in open-world…
Improving GAN Training via Feature Space Shrinkage
Haozhe Liu, Wentian Zhang, Bing Li +6
Due to the outstanding capability for data generation, Generative Adversarial Networks (GANs) have attracted considerable attention in unsupervised learning. However, training GANs…
Decoupled Mixup for Generalized Visual Recognition
Haozhe Liu, Wentian Zhang, Jinheng Xie +7
Convolutional neural networks (CNN) have demonstrated remarkable performance when the training and testing data are from the same distribution. However, such trained CNN models oft…
A Uniform Representation Learning Method for OCT-based Fingerprint Presentation Attack Detection and Reconstruction
Wentian Zhang, Haozhe Liu, Feng Liu +1
The technology of optical coherence tomography (OCT) to fingerprint imaging opens up a new research potential for fingerprint recognition owing to its ability to capture depth info…
A Benchmark for Weakly Semi-Supervised Abnormality Localization in Chest X-Rays
Haoqin Ji, Haozhe Liu, Yuexiang Li +7
Accurate abnormality localization in chest X-rays (CXR) can benefit the clinical diagnosis of various thoracic diseases. However, the lesion-level annotation can only be performed…
Combating Mode Collapse in GANs via Manifold Entropy Estimation
Haozhe Liu, Bing Li, Haoqian Wu +5
Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications in recent years. However, mode collapse remains a critical problem in GANs. I…
Activation Template Matching Loss for Explainable Face Recognition
Huawei Lin, Haozhe Liu, Qiufu Li +1
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 additionals…
Robust Representation via Dynamic Feature Aggregation
Haozhe Liu, Haoqin Ji, Yuexiang Li +5
Deep convolutional neural network (CNN) based models are vulnerable to the adversarial attacks. One of the possible reasons is that the embedding space of CNN based model is sparse…
Scene Consistency Representation Learning for Video Scene Segmentation
Haoqian Wu, Keyu Chen, Yanan Luo +5
A long-term video, such as a movie or TV show, is composed of various scenes, each of which represents a series of shots sharing the same semantic story. Spotting the correct scene…
FRT-PAD: Effective Presentation Attack Detection Driven by Face Related Task
Wentian Zhang, Haozhe Liu, Feng Liu +2
The robustness and generalization ability of Presentation Attack Detection (PAD) methods is critical to ensure the security of Face Recognition Systems (FRSs). However, in a real s…
Group-wise Inhibition based Feature Regularization for Robust Classification
Haozhe Liu, Haoqian Wu, Weicheng Xie +2
The convolutional neural network (CNN) is vulnerable to degraded images with even very small variations (e.g. corrupted and adversarial samples). One of the possible reasons is tha…
A Zero-Shot based Fingerprint Presentation Attack Detection System
Haozhe Liu, Wentian Zhang, Guojie Liu +1
With the development of presentation attacks, Automated Fingerprint Recognition Systems(AFRSs) are vulnerable to presentation attack. Thus, numerous methods of presentation attack…