38 citations · 82 across the 16 of their papers we have counts for
17 papers
MeanSR: Restoration Trajectory Learning for One-Step Perceptual Super-Resolution
Axi Niu, Jiawei Kou, Kang Zhang +3
Diffusion-based super-resolution (SR) achieves strong perceptual quality but requires costly iterative denoising. Existing one-step distillation methods reduce inference time but d…
FaithIR: Rethinking Infrared Image Super-Resolution from Perceptual Sharpness to Task Relevant Fidelity
Axi Niu, Zhenguo Wu, Kang Zhang +3
Infrared image super-resolution (IISR) is important for downstream tasks such as object detection and semantic segmentation. Existing IISR methods often produce artificial textures…
A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion Transformers
Trung X. Pham, Kang Zhang, Ji Woo Hong +1
Diffusion Transformers have achieved state-of-the-art performance in class-conditional and multimodal generation, yet the structure of their learned conditional embeddings remains…
Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
Chenshuang Zhang, Kang Zhang, Joon Son Chung +3
Distinguishing visually similar objects by their motion remains a critical challenge in computer vision. Although supervised trackers show promise, contemporary self-supervised tra…
Towards Understanding Dual BN In Hybrid Adversarial Training
Chenshuang Zhang, Chaoning Zhang, Kang Zhang +3
There is a growing concern about applying batch normalization (BN) in adversarial training (AT), especially when the model is trained on both adversarial samples and clean samples…
DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based Single Image Super-resolution
Axi Niu, Kang Zhang, Joshua Tian Jin Tee +5
It is well known the adversarial optimization of GAN-based image super-resolution (SR) methods makes the preceding SR model generate unpleasant and undesirable artifacts, leading t…
ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution
Axi Niu, Pham Xuan Trung, Kang Zhang +4
Diffusion models have gained significant popularity in the field of image-to-image translation. Previous efforts applying diffusion models to image super-resolution (SR) have demon…
Learning from Multi-Perception Features for Real-Word Image Super-resolution
Axi Niu, Kang Zhang, Trung X. Pham +4
Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-es…
CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution
Axi Niu, Kang Zhang, Trung X. Pham +4
Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation to generate high-quality images. Prior attempts at applying the DPM to image super-resol…
On the Pros and Cons of Momentum Encoder in Self-Supervised Visual Representation Learning
Trung Pham, Chaoning Zhang, Axi Niu +2
Exponential Moving Average (EMA or momentum) is widely used in modern self-supervised learning (SSL) approaches, such as MoCo, for enhancing performance. We demonstrate that such m…
A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond
Chaoning Zhang, Chenshuang Zhang, Junha Song +3
Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar tr…
Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness
Chaoning Zhang, Kang Zhang, Chenshuang Zhang +4
Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for unsupervised representation learning are two active research fields. Integrating…
Understanding and Improving Group Normalization
Agus Gunawan, Xu Yin, Kang Zhang
Various normalization layers have been proposed to help the training of neural networks. Group Normalization (GN) is one of the effective and attractive studies that achieved signi…
Investigating Top- White-Box and Transferable Black-box Attack
Chaoning Zhang, Philipp Benz, Adil Karjauv +3
Existing works have identified the limitation of top- attack success rate (ASR) as a metric to evaluate the attack strength but exclusively investigated it in the white-box sett…
Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo
Chaoning Zhang, Kang Zhang, Trung X. Pham +4
Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior b…
How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning
Chaoning Zhang, Kang Zhang, Chenshuang Zhang +3
To avoid collapse in self-supervised learning (SSL), a contrastive loss is widely used but often requires a large number of negative samples. Without negative samples yet achieving…
Fast Adversarial Training with Noise Augmentation: A Unified Perspective on RandStart and GradAlign
Axi Niu, Kang Zhang, Chaoning Zhang +4
PGD-based and FGSM-based are two popular adversarial training (AT) approaches for obtaining adversarially robust models. Compared with PGD-based AT, FGSM-based one is significantly…