activity
20182023
most citedFECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network

105 citations · 183 across the 15 of their papers we have counts for

collaborators

27 papers

cs.LG2023★ 9 cited

CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification

Nan Yin, Li Shen, Mengzhu Wang +5

Although graph neural networks (GNNs) have achieved impressive achievements in graph classification, they often need abundant task-specific labels, which could be extensively costl…

cs.CV2023★ 4 cited

PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction

Hao Wu, Fan Xu, Chong Chen +3

In this paper, we investigate the challenge of spatio-temporal video prediction task, which involves generating future video frames based on historical spatio-temporal observation…

cs.CV2023

Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation

Deyi Ji, Haoran Wang, Mingyuan Tao +3

Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student. However, low-level texture kno…

cs.CV2023★ 105 cited

FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network

Huafeng Liu, Pai Peng, Tao Chen +3

Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images. The current correlation-…

cs.CV2022★ 1 cited

Rethinking IoU-based Optimization for Single-stage 3D Object Detection

Hualian Sheng, Sijia Cai, Na Zhao +5

Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and class…

cs.CV2022★ 3 cited

Online Convolutional Re-parameterization

Mu Hu, Junyi Feng, Jiashen Hua +4

Structural re-parameterization has drawn increasing attention in various computer vision tasks. It aims at improving the performance of deep models without introducing any inferenc…