Search Results for author:
Found 10 papers, 6 papers with code
Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners
In this paper, we argue that large models such as vision and language transformers pre-trained on large datasets can be excellent few-shot incremental learners.
GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap
We specifically focus on scenarios with a substantial domain gap, in contrast to existing works primarily deal with small domain gaps between labeled source domains and unlabeled target domains.
RADIO: Reference-Agnostic Dubbing Video Synthesis
One of the most challenging problems in audio-driven talking head generation is achieving high-fidelity detail while ensuring precise synchronization.
LFS-GAN: Lifelong Few-Shot Image Generation
Surprisingly, we find that our LFS-GAN even outperforms the existing few-shot GANs in the few-shot image generation task.
Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning
In addition, to alleviate the class imbalance problem, we introduce a new gradient similarity-based focal loss and adaptive feature scaling to ease overfitting to the major classes and underfitting to the minor classes.
One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era
Overall, this work is the first to survey ChatGPT with a comprehensive review of its underlying technology, applications, and challenges.
LINe: Out-of-Distribution Detection by Leveraging Important Neurons
In this study, from the perspective of neurons in the deep layer of the model representing high-level features, we introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data.
Ranked #1 on
Out-of-Distribution Detection
on ImageNet-1k vs SUN
WaGI : Wavelet-based GAN Inversion for Preserving High-frequency Image Details
Especially, we prove that the widely-used loss term in GAN inversion, i. e., L2, is biased to reconstruct low-frequency features mainly.
IntereStyle: Encoding an Interest Region for Robust StyleGAN Inversion
In this paper, we point out that the existing encoders try to lower the distortion not only on the interest region, e. g., human facial region but also on the uninterest region, e. g., background patterns and obstacles.
Continual Unsupervised Domain Adaptation for Semantic Segmentation
Our novel ETM framework contains Target-specific Memory (TM) for each target domain to alleviate catastrophic forgetting.
