4 citations · 12 across the 21 of their papers we have counts for
21 papers
Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection
Jingyao Wang, Yiming Chen, Lingyu Si +1
Scene understanding is one of the core tasks in computer vision, aiming to extract semantic information from images to identify objects, scene categories, and their interrelationsh…
On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation
Wenwen Qiang, Ziyin Gu, Lingyu Si +4
In this paper, we addressed the limitation of relying solely on distribution alignment and source-domain empirical risk minimization in Unsupervised Domain Adaptation (UDA). Our in…
Less yet robust: crucial region selection for scene recognition
Jianqi Zhang, Mengxuan Wang, Jingyao Wang +3
Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on co…
Rethinking Meta-Learning from a Learning Lens
Jingyao Wang, Wenwen Qiang, Changwen Zheng +2
Meta-learning seeks to learn a well-generalized model initialization from training tasks to solve unseen tasks. From the "learning to learn" perspective, the quality of the initial…
Towards the Causal Complete Cause of Multi-Modal Representation Learning
Jingyao Wang, Siyu Zhao, Wenwen Qiang +4
Multi-Modal Learning (MML) aims to learn effective representations across modalities for accurate predictions. Existing methods typically focus on modality consistency and specific…
A Physical Model-Guided Framework for Underwater Image Enhancement and Depth Estimation
Dazhao Du, Lingyu Si, Fanjiang Xu +2
Due to the selective absorption and scattering of light by diverse aquatic media, underwater images usually suffer from various visual degradations. Existing underwater image enhan…
On the Universality of Self-Supervised Learning
Wenwen Qiang, Jingyao Wang, Changwen Zheng +2
In this paper, we investigate what constitutes a good representation or model in self-supervised learning (SSL). We argue that a good representation should exhibit universality, ch…
Self-Supervised Representation Learning with Meta Comprehensive Regularization
Huijie Guo, Ying Ba, Jie Hu +3
Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deforma…
Rethinking Causal Relationships Learning in Graph Neural Networks
Hang Gao, Chengyu Yao, Jiangmeng Li +5
Graph Neural Networks (GNNs) demonstrate their significance by effectively modeling complex interrelationships within graph-structured data. To enhance the credibility and robustne…
UIEDP:Underwater Image Enhancement with Diffusion Prior
Dazhao Du, Enhan Li, Lingyu Si +3
Underwater image enhancement (UIE) aims to generate clear images from low-quality underwater images. Due to the unavailability of clear reference images, researchers often synthesi…
PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classification
Meijuan Su, Feihong He, Fanzhang Li
Few-shot image classification has received considerable attention for overcoming the challenge of limited classification performance with limited samples in novel classes. Most exi…
Cartoondiff: Training-free Cartoon Image Generation with Diffusion Transformer Models
Feihong He, Gang Li, Lingyu Si +4
Image cartoonization has attracted significant interest in the field of image generation. However, most of the existing image cartoonization techniques require re-training models u…
Background Debiased SAR Target Recognition via Causal Interventional Regularizer
Hongwei Dong, Fangzhou Han, Lingyu Si +2
Recent studies have utilized deep learning (DL) techniques to automatically extract features from synthetic aperture radar (SAR) images, which shows great promise for enhancing the…
A Dimensional Structure based Knowledge Distillation Method for Cross-Modal Learning
Lingyu Si, Hongwei Dong, Wenwen Qiang +5
Due to limitations in data quality, some essential visual tasks are difficult to perform independently. Introducing previously unavailable information to transfer informative dark…
Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective
Hang Gao, Jiangmeng Li, Wenwen Qiang +5
Benefiting from the injection of human prior knowledge, graphs, as derived discrete data, are semantically dense so that models can efficiently learn the semantic information from…
Timestamp-Supervised Action Segmentation from the Perspective of Clustering
Dazhao Du, Enhan Li, Lingyu Si +2
Video action segmentation under timestamp supervision has recently received much attention due to lower annotation costs. Most existing methods generate pseudo-labels for all frame…
Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspective
Jiangmeng Li, Yanan Zhang, Wenwen Qiang +5
Few-shot learning models learn representations with limited human annotations, and such a learning paradigm demonstrates practicability in various tasks, e.g., image classification…
Robust Causal Graph Representation Learning against Confounding Effects
Hang Gao, Jiangmeng Li, Wenwen Qiang +4
The prevailing graph neural network models have achieved significant progress in graph representation learning. However, in this paper, we uncover an ever-overlooked phenomenon: th…
Do we really need temporal convolutions in action segmentation?
Dazhao Du, Bing Su, Yu Li +3
Action classification has made great progress, but segmenting and recognizing actions from long untrimmed videos remains a challenging problem. Most state-of-the-art methods focus…
Bootstrapping Informative Graph Augmentation via A Meta Learning Approach
Hang Gao, Jiangmeng Li, Wenwen Qiang +3
Recent works explore learning graph representations in a self-supervised manner. In graph contrastive learning, benchmark methods apply various graph augmentation approaches. Howev…
SimViT: Exploring a Simple Vision Transformer with sliding windows
Gang Li, Di Xu, Xing Cheng +2
Although vision Transformers have achieved excellent performance as backbone models in many vision tasks, most of them intend to capture global relations of all tokens in an image…