Due to the difficulty in scaling up, generative adversarial networks (GA...
The success of style-based generators largely benefits from style modula...
Prompt tuning and adapter tuning have shown great potential in transferr...
Despite the rapid advance of 3D-aware image synthesis, existing studies
...
The crux of label-efficient semantic segmentation is to produce high-qua...
Semantic segmentation usually suffers from a long-tail data distribution...
The pursuit of controllability as a higher standard of visual content
cr...
Domain adaptive semantic segmentation aims to transfer knowledge from a
...
A good metric, which promises a reliable comparison between solutions, i...
Video temporal grounding aims to pinpoint a video segment that matches t...
Foundation models are pre-trained on massive data and transferred to
dow...
Recent large-scale generative models learned on big data are capable of
...
This work presents a unified knowledge protocol, called UKnow, which
fac...
Generative models make huge progress to the photorealistic image synthes...
Recent years witness the tremendous success of generative adversarial
ne...
Existing 3D-aware image synthesis approaches mainly focus on generating ...
Video generation requires synthesizing consistent and persistent frames ...
Diffusion models, which learn to reverse a signal destruction process to...
This work presents two astonishing findings on neural networks learned f...
Generative models, as an important family of statistical modeling, targe...
Discriminator plays a vital role in training generative adversarial netw...
Self-training has shown great potential in semi-supervised learning. Its...
Despite the rapid advance of unsupervised anomaly detection, existing me...
Inverting a Generative Adversarial Network (GAN) facilitates a wide rang...
The crux of semi-supervised semantic segmentation is to assign adequate
...
Making generative models 3D-aware bridges the 2D image space and the 3D
...
Semi-supervised action recognition is a challenging but important task d...
The success of Generative Adversarial Networks (GANs) is largely built u...
This work aims at transferring a Generative Adversarial Network (GAN)
pr...
Convolutional Neural Networks (CNNs) have achieved remarkable success in...
Generative Adversarial Networks (GANs) have significantly advanced image...
Generative Adversarial Networks (GANs) have made great success in
synthe...
In this work, we study the image transformation problem by learning the
...
Generative Adversarial Networks (GANs) have recently advanced face synth...
Generative Adversarial Networks (GANs) have recently advanced image synt...
A rich set of semantic attributes has been shown to emerge in the latent...
Although Generative Adversarial Networks (GANs) have made significant
pr...
Recent work has shown that a variety of controllable semantics emerges i...
Knowledge distillation (KD) is one of the most potent ways for model
com...
Despite the success of Generative Adversarial Networks (GANs) in image
s...
Despite the success of Generative Adversarial Networks (GANs) in image
s...
Despite the recent advance of Generative Adversarial Networks (GANs) in
...
Convolutional Neural Networks (CNNs) become deeper and deeper in recent
...
The advance of Generative Adversarial Networks (GANs) enables realistic ...