Search Results - "Pham, Trung X"

ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution by Niu, Axi, Pham, Trung X., Zhang, Kang, Sun, Jinqiu, Zhu, Yu, Yan, Qingsen, Kweon, In So, Zhang, Yanning

“…Diffusion models have gained significant popularity for image-to-image translation tasks. Previous efforts applying diffusion models to image super-resolution…”
Get full text

CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution by Niu, Axi, Zhang, Kang, Pham, Trung X., Sun, Jinqiu, Zhu, Yu, Kweon, In So, Zhang, Yanning

“…Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation to generate high-quality images. Prior attempts at applying the DPM…”
Get full text

Learning from Multi-Perception Features for Real-Word Image Super-resolution by Niu, Axi, Zhang, Kang, Pham, Trung X., Wang, Pei, Sun, Jinqiu, Kweon, In So, Zhang, Yanning

“…Actual image super-resolution is an extremely challenging task due to complex degradations existing in the image. To solve this problem, two dominant…”
Get full text

Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo by Zhang, Chaoning, Zhang, Kang, Pham, Trung X., Niu, Axi, Qiao, Zhinan, Yoo, Chang D., Kweon, In So

“…Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free…”
Get full text

MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation by Pham, Trung X, Ton, Tri, Yoo, Chang D

“…We introduce MDSGen, a novel framework for vision-guided open-domain sound generation optimized for model parameter size, memory consumption, and inference…”
Get full text

Cross-view Masked Diffusion Transformers for Person Image Synthesis by Pham, Trung X, Kang, Zhang, Yoo, Chang D

“…We present X-MDPT ($\underline{Cross}$-view $\underline{M}$asked $\underline{D}$iffusion $\underline{P}$rediction $\underline{T}$ransformers), a novel…”
Get full text

Learning from Multi-Perception Features for Real-Word Image Super-resolution by Niu, Axi, Zhang, Kang, Pham, Trung X, Wang, Pei, Sun, Jinqiu, Kweon, In So, Zhang, Yanning

“…Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods…”
Get full text

CDPMSR: Conditional Diffusion Probabilistic Models for Single Image Super-Resolution by Niu, Axi, Zhang, Kang, Pham, Trung X, Sun, Jinqiu, Zhu, Yu, Kweon, In So, Zhang, Yanning

“…Diffusion probabilistic models (DPM) have been widely adopted in image-to-image translation to generate high-quality images. Prior attempts at applying the DPM…”
Get full text

How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning by Zhang, Chaoning, Zhang, Kang, Zhang, Chenshuang, Pham, Trung X, Yoo, Chang D, Kweon, In So

“…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…”
Get full text

DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based Single Image Super-resolution by Niu, Axi, Zhang, Kang, Tee, Joshua Tian Jin, Pham, Trung X, Sun, Jinqiu, Yoo, Chang D, Kweon, In So, Zhang, Yanning

“…It is well known the adversarial optimization of GAN-based image super-resolution (SR) methods makes the preceding SR model generate unpleasant and undesirable…”
Get full text

Self-supervised Learning with Local Attention-Aware Feature by Pham, Trung X, Mina, Rusty John Lloyd, Issa, Dias, Yoo, Chang D

“…In this work, we propose a novel methodology for self-supervised learning for generating global and local attention-aware visual features. Our approach is…”
Get full text

Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution by Vu, Thang, Jang, Hyunjun, Pham, Trung X, Yoo, Chang D

“…This paper considers an architecture referred to as Cascade Region Proposal Network (Cascade RPN) for improving the region-proposal quality and detection…”
Get full text

Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo by Zhang, Chaoning, Zhang, Kang, Pham, Trung X, Niu, Axi, Qiao, Zhinan, Yoo, Chang D, Kweon, In So

“…Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free…”
Get full text

Self-Supervised Visual Representation Learning via Residual Momentum by Pham, Trung X, Niu, Axi, Kang, Zhang, Madjid, Sultan Rizky, Hong, Ji Woo, Kim, Daehyeok, Tee, Joshua Tian Jin, Yoo, Chang D

“…Self-supervised learning (SSL) approaches have shown promising capabilities in learning the representation from unlabeled data. Amongst them, momentum-based…”
Get full text

PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report by Ignatov, Andrey, Timofte, Radu, Van Vu, Thang, Luu, Tung Minh, Pham, Trung X, Van Nguyen, Cao, Kim, Yongwoo, Choi, Jae-Seok, Kim, Munchurl, Huang, Jie, Ran, Jiewen, Xing, Chen, Zhou, Xingguang, Zhu, Pengfei, Geng, Mingrui, Li, Yawei, Agustsson, Eirikur, Gu, Shuhang, Van Gool, Luc, de Stoutz, Etienne, Kobyshev, Nikolay, Nie, Kehui, Zhao, Yan, Li, Gen, Tong, Tong, Gao, Qinquan, Hanwen, Liu, Michelini, Pablo Navarrete, Dan, Zhu, Fengshuo, Hu, Hui, Zheng, Wang, Xiumei, Deng, Lirui, Meng, Rang, Qin, Jinghui, Shi, Yukai, Wen, Wushao, Lin, Liang, Feng, Ruicheng, Wu, Shixiang, Dong, Chao, Qiao, Yu, Vasu, Subeesh, Madam, Nimisha Thekke, Kandula, Praveen, Rajagopalan, A. N, Liu, Jie, Jung, Cheolkon

“…This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones. The challenge…”
Get full text