105 citations · 433 across the 42 of their papers we have counts for
13 papers · 1 filter
Order-preserving Consistency Regularization for Domain Adaptation and Generalization
Mengmeng Jing, Xiantong Zhen, Jingjing Li +1
Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this…
Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models
Baoshuo Kan, Teng Wang, Wenpeng Lu +3
Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve st…
Probabilistic Test-Time Generalization by Variational Neighbor-Labeling
Sameer Ambekar, Zehao Xiao, Jiayi Shen +2
This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed on unseen target domains. We follow the strict separation…
Lightweight Improved Residual Network for Efficient Inverse Tone Mapping
Liqi Xue, Tianyi Xu, Yongbao Song +4
The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the int…
EMO: Episodic Memory Optimization for Few-Shot Meta-Learning
Yingjun Du, Jiayi Shen, Xiantong Zhen +1
Few-shot meta-learning presents a challenge for gradient descent optimization due to the limited number of training samples per task. To address this issue, we propose an episodic…
MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
Wenfang Sun, Yingjun Du, Xiantong Zhen +3
Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily avai…
CageViT: Convolutional Activation Guided Efficient Vision Transformer
Hao Zheng, Jinbao Wang, Xiantong Zhen +3
Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input…
SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail
Yingjun Du, Jiayi Shen, Xiantong Zhen +1
Modern image classifiers perform well on populated classes, while degrading considerably on tail classes with only a few instances. Humans, by contrast, effortlessly handle the lon…
Parameter-Free Channel Attention for Image Classification and Super-Resolution
Yuxuan Shi, Lingxiao Yang, Wangpeng An +2
The channel attention mechanism is a useful technique widely employed in deep convolutional neural networks to boost the performance for image processing tasks, eg, image classific…
Implicit Diffusion Models for Continuous Super-Resolution
Sicheng Gao, Xuhui Liu, Bohan Zeng +6
Image super-resolution (SR) has attracted increasing attention due to its wide applications. However, current SR methods generally suffer from over-smoothing and artifacts, and mos…
Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning
Ivona Najdenkoska, Xiantong Zhen, Marcel Worring
Multimodal few-shot learning is challenging due to the large domain gap between vision and language modalities. Existing methods are trying to communicate visual concepts as prompt…
Energy-Based Test Sample Adaptation for Domain Generalization
Zehao Xiao, Xiantong Zhen, Shengcai Liao +1
In this paper, we propose energy-based sample adaptation at test time for domain generalization. Where previous works adapt their models to target domains, we adapt the unseen targ…
CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension
Zhi Zhang, Helen Yannakoudakis, Xiantong Zhen +1
The task of multimodal referring expression comprehension (REC), aiming at localizing an image region described by a natural language expression, has recently received increasing a…