56 citations · 221 across the 25 of their papers we have counts for
24 papers · 1 filter
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data
Jiangming Shi, Shanshan Zheng, Xiangbo Yin +3
Federated learning (FL) provides a decentralized machine learning paradigm where a server collaborates with a group of clients to learn a global model without accessing the clients…
Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
Yujun Chen, Xin Tan, Zhizhong Zhang +2
As the exorbitant expense of labeling autopilot datasets and the growing trend of utilizing unlabeled data, semi-supervised segmentation on point clouds becomes increasingly impera…
COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
Qihang Ma, Xin Tan, Yanyun Qu +3
The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabiliti…
BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentation
Miaoyu Li, Yachao Zhang, Xu MA +2
Cross-modal Unsupervised Domain Adaptation (UDA) aims to exploit the complementarity of 2D-3D data to overcome the lack of annotation in a new domain. However, UDA methods rely on…
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
Yachao Zhang, Zonghao Li, Yuan Xie +3
Existing methods for large-scale point cloud semantic segmentation require expensive, tedious and error-prone manual point-wise annotations. Intuitively, weakly supervised training…
Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning
Tianfang Sun, Zhizhong Zhang, Xin Tan +3
Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which re…
Variational Distillation for Multi-View Learning
Xudong Tian, Zhizhong Zhang, Cong Wang +6
Information Bottleneck (IB) based multi-view learning provides an information theoretic principle for seeking shared information contained in heterogeneous data descriptions. Howev…
Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
Jiaqi Gao, Jingqi Li, Hongming Shan +4
Crowd counting has important applications in public safety and pandemic control. A robust and practical crowd counting system has to be capable of continuously learning with the ne…
Towards Compact Single Image Super-Resolution via Contrastive Self-distillation
Yanbo Wang, Shaohui Lin, Yanyun Qu +4
Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead…
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
Jingyu Gong, Jiachen Xu, Xin Tan +4
Hidden features in neural network usually fail to learn informative representation for 3D segmentation as supervisions are only given on output prediction, while this can be solved…
Contrastive Learning for Compact Single Image Dehazing
Haiyan Wu, Yanyun Qu, Shaohui Lin +5
Single image dehazing is a challenging ill-posed problem due to the severe information degeneration. However, existing deep learning based dehazing methods only adopt clear images…
Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification
Xudong Tian, Zhizhong Zhang, Shaohui Lin +3
The Information Bottleneck (IB) provides an information theoretic principle for representation learning, by retaining all information relevant for predicting label while minimizing…
Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds
Jingyu Gong, Jiachen Xu, Xin Tan +4
Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in fe…
NTIRE 2020 Challenge on NonHomogeneous Dehazing
Codruta O. Ancuti, Cosmin Ancuti, Florin-Alexandru Vasluianu +49
This paper reviews the NTIRE 2020 Challenge on NonHomogeneous Dehazing of images (restoration of rich details in hazy image). We focus on the proposed solutions and their results e…
NTIRE 2020 Challenge on Image Demoireing: Methods and Results
Shanxin Yuan, Radu Timofte, Ales Leonardis +43
This paper reviews the Challenge on Image Demoireing that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2020. Demo…
Meta Segmentation Network for Ultra-Resolution Medical Images
Tong Wu, Yuan Xie, Yanyun Qu +2
Despite recent progress on semantic segmentation, there still exist huge challenges in medical ultra-resolution image segmentation. The methods based on multi-branch structure can…
Novelty Detection via Non-Adversarial Generative Network
Chengwei Chen, Wang Yuan, Yuan Xie +4
One-class novelty detection is the process of determining if a query example differs from the training examples (the target class). Most of previous strategies attempt to learn the…
UG Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments
Ye Yuan, Wenhan Yang, Wenqi Ren +3
The UG challenge in IEEE CVPR 2019 aims to evoke a comprehensive discussion and exploration about how low-level vision techniques can benefit the high-level automatic visual…
Bi-GANs-ST for Perceptual Image Super-resolution
Xiaotong Luo, Rong Chen, Yuan Xie +2
Image quality measurement is a critical problem for image super-resolution (SR) algorithms. Usually, they are evaluated by some well-known objective metrics, e.g., PSNR and SSIM, b…
Jointly Deep Multi-View Learning for Clustering Analysis
Bingqian Lin, Yuan Xie, Yanyun Qu +2
In this paper, we propose a novel Joint framework for Deep Multi-view Clustering (DMJC), where multiple deep embedded features, multi-view fusion mechanism and clustering assignmen…
Robust Kernelized Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
Yanyun Qu, Jinyan Liu, Yuan Xie +1
Most recently, tensor-SVD is implemented on multi-view self-representation clustering and has achieved the promising results in many real-world applications such as face clustering…
Joint Hierarchical Category Structure Learning and Large-Scale Image Classification
Yanyun Qu, Li Lin, Fumin Shen +4
We investigate the scalable image classification problem with a large number of categories. Hierarchical visual data structures are helpful for improving the efficiency and perform…
On Unifying Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
Yuan Xie, Dacheng Tao, Wensheng Zhang +3
In this paper, we address the multi-view subspace clustering problem. Our method utilizes the circulant algebra for tensor, which is constructed by stacking the subspace representa…
Distortion-driven Turbulence Effect Removal using Variational Model
Yuan Xie, Wensheng Zhang, Dacheng Tao +3
It remains a challenge to simultaneously remove geometric distortion and space-time-varying blur in frames captured through a turbulent atmospheric medium. To solve, or at least re…