b'Yujun Shen'

research

∙ 09/07/2023

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

Due to the difficulty in scaling up, generative adversarial networks (GA...

0 Jiapeng Zhu, et al. ∙

research

∙ 08/29/2023

Learning Modulated Transformation in GANs

The success of style-based generators largely benefits from style modula...

0 Ceyuan Yang, et al. ∙

research

∙ 07/27/2023

Regularized Mask Tuning: Uncovering Hidden Knowledge in Pre-trained Vision-Language Models

Prompt tuning and adapter tuning have shown great potential in transferr...

0 Kecheng Zheng, et al. ∙

research

∙ 06/21/2023

Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase

Despite the rapid advance of 3D-aware image synthesis, existing studies ...

0 Qiuyu Wang, et al. ∙

research

∙ 06/04/2023

Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation

The crux of label-efficient semantic segmentation is to produce high-qua...

0 Haochen Wang, et al. ∙

research

∙ 06/03/2023

Balancing Logit Variation for Long-tailed Semantic Segmentation

Semantic segmentation usually suffers from a long-tail data distribution...

0 Yuchao Wang, et al. ∙

research

∙ 06/03/2023

VideoComposer: Compositional Video Synthesis with Motion Controllability

The pursuit of controllability as a higher standard of visual content cr...

0 Xiang Wang, et al. ∙

research

∙ 05/23/2023

Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation

Domain adaptive semantic segmentation aims to transfer knowledge from a ...

0 Haochen Wang, et al. ∙

research

∙ 04/04/2023

Revisiting the Evaluation of Image Synthesis with GANs

A good metric, which promises a reliable comparison between solutions, i...

4 Mengping Yang, et al. ∙

research

∙ 03/15/2023

Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos

Video temporal grounding aims to pinpoint a video segment that matches t...

0 Yulin Pan, et al. ∙

research

∙ 03/13/2023

ViM: Vision Middleware for Unified Downstream Transferring

Foundation models are pre-trained on massive data and transferred to dow...

0 Yutong Feng, et al. ∙

research

∙ 02/20/2023

Composer: Creative and Controllable Image Synthesis with Composable Conditions

Recent large-scale generative models learned on big data are capable of ...

0 Lianghua Huang, et al. ∙

research

∙ 02/14/2023

UKnow: A Unified Knowledge Protocol for Common-Sense Reasoning and Vision-Language Pre-training

This work presents a unified knowledge protocol, called UKnow, which fac...

0 Biao Gong, et al. ∙

research

∙ 01/20/2023

Spatial Steerability of GANs via Self-Supervision from Discriminator

Generative models make huge progress to the photorealistic image synthes...

19 Jianyuan Wang, et al. ∙

research

∙ 01/12/2023

GH-Feat: Learning Versatile Generative Hierarchical Features from GANs

Recent years witness the tremendous success of generative adversarial ne...

8 Yinghao Xu, et al. ∙

research

∙ 12/22/2022

DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis

Existing 3D-aware image synthesis approaches mainly focus on generating ...

3 Yinghao Xu, et al. ∙

research

∙ 12/14/2022

Towards Smooth Video Composition

Video generation requires synthesizing consistent and persistent frames ...

4 Qihang Zhang, et al. ∙

research

∙ 11/29/2022

Dimensionality-Varying Diffusion Process

Diffusion models, which learn to reverse a signal destruction process to...

0 Han Zhang, et al. ∙

research

∙ 11/21/2022

Neural Dependencies Emerging from Learning Massive Categories

This work presents two astonishing findings on neural networks learned f...

0 Ruili Feng, et al. ∙

research

∙ 10/27/2022

Deep Generative Models on 3D Representations: A Survey

Generative models, as an important family of statistical modeling, targe...

0 Zifan Shi, et al. ∙

research

∙ 09/20/2022

Improving GANs with A Dynamic Discriminator

Discriminator plays a vital role in training generative adversarial netw...

7 Ceyuan Yang, et al. ∙

research

∙ 09/15/2022

Learning from Future: A Novel Self-Training Framework for Semantic Segmentation

Self-training has shown great potential in semi-supervised learning. Its...

0 Ye Du, et al. ∙

research

∙ 06/08/2022

A Unified Model for Multi-class Anomaly Detection

Despite the rapid advance of unsupervised anomaly detection, existing me...

15 Zhiyuan You, et al. ∙

research

∙ 03/21/2022

High-fidelity GAN Inversion with Padding Space

Inverting a Generative Adversarial Network (GAN) facilitates a wide rang...

6 Qingyan Bai, et al. ∙

research

∙ 03/08/2022

Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

The crux of semi-supervised semantic segmentation is to assign adequate ...

12 Yuchao Wang, et al. ∙

research

∙ 12/20/2021

3D-aware Image Synthesis via Learning Structural and Textural Representations

Making generative models 3D-aware bridges the 2D image space and the 3D ...

7 Yinghao Xu, et al. ∙

research

∙ 12/17/2021

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

Semi-supervised action recognition is a challenging but important task d...

15 Yinghao Xu, et al. ∙

research

∙ 12/01/2021

Improving GAN Equilibrium by Raising Spatial Awareness

The success of Generative Adversarial Networks (GANs) is largely built u...

2 Jianyuan Wang, et al. ∙

research

∙ 11/18/2021

One-Shot Generative Domain Adaptation

This work aims at transferring a Generative Adversarial Network (GAN) pr...

2 Ceyuan Yang, et al. ∙

research

∙ 06/19/2021

CompConv: A Compact Convolution Module for Efficient Feature Learning

Convolutional Neural Networks (CNNs) have achieved remarkable success in...

6 Chen Zhang, et al. ∙

research

∙ 06/08/2021

Data-Efficient Instance Generation from Instance Discrimination

Generative Adversarial Networks (GANs) have significantly advanced image...

2 Ceyuan Yang, et al. ∙

research

∙ 05/18/2021

Decorating Your Own Bedroom: Locally Controlling Image Generation with Generative Adversarial Networks

Generative Adversarial Networks (GANs) have made great success in synthe...

8 Chen Zhang, et al. ∙

research

∙ 03/13/2021

Unsupervised Image Transformation Learning via Generative Adversarial Networks

In this work, we study the image transformation problem by learning the ...

23 Kaiwen Zha, et al. ∙

research

∙ 12/09/2020

Improving the Fairness of Deep Generative Models without Retraining

Generative Adversarial Networks (GANs) have recently advanced face synth...

15 Shuhan Tan, et al. ∙

research

∙ 07/20/2020

Generative Hierarchical Features from Synthesizing Images

Generative Adversarial Networks (GANs) have recently advanced image synt...

28 Yinghao Xu, et al. ∙

research

∙ 07/13/2020

Closed-Form Factorization of Latent Semantics in GANs

A rich set of semantic attributes has been shown to emerge in the latent...

1 Yujun Shen, et al. ∙

research

∙ 05/18/2020

InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs

Although Generative Adversarial Networks (GANs) have made significant pr...

8 Yujun Shen, et al. ∙

research

∙ 03/31/2020

In-Domain GAN Inversion for Real Image Editing

Recent work has shown that a variety of controllable semantics emerges i...

0 Jiapeng Zhu, et al. ∙

research

∙ 02/21/2020

Residual Knowledge Distillation

Knowledge distillation (KD) is one of the most potent ways for model com...

34 Mengya Gao, et al. ∙

research

∙ 12/15/2019

Image Processing Using Multi-Code GAN Prior

Despite the success of Generative Adversarial Networks (GANs) in image s...

51 Jinjin Gu, et al. ∙

research

∙ 11/21/2019

Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis

Despite the success of Generative Adversarial Networks (GANs) in image s...

13 Ceyuan Yang, et al. ∙

research

∙ 07/25/2019

Interpreting the Latent Space of GANs for Semantic Face Editing

Despite the recent advance of Generative Adversarial Networks (GANs) in ...

2 Yujun Shen, et al. ∙

research

∙ 12/05/2018

Feature Matters: A Stage-by-Stage Approach for Knowledge Transfer

Convolutional Neural Networks (CNNs) become deeper and deeper in recent ...

8 Mengya Gao, et al. ∙

research

∙ 12/04/2018

FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis

The advance of Generative Adversarial Networks (GANs) enables realistic ...

8 Yujun Shen, et al. ∙

Yujun Shen

Featured Co-authors