activity
20172022
most citedBSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification

217 citations · 416 across the 16 of their papers we have counts for

collaborators
Showing cs.CVShow all

23 papers · 1 filter

cs.CV2022★ 66 cited

Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes

Xi Weng, Yan Yan, Si Chen +2

Over the past few years, deep convolutional neural network-based methods have made great progress in semantic segmentation of street scenes. Some recent methods align feature maps…

cs.CV2022

When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework

Xinyi Zou, Yan Yan, Jing-Hao Xue +2

Human emotions involve basic and compound facial expressions. However, current research on facial expression recognition (FER) mainly focuses on basic expressions, and thus fails t…

cs.CV2021

APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation

Jiacheng Chen, Bin-Bin Gao, Zongqing Lu +3

Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning…

cs.CV2021

Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments

Xiaoxu Li, Xiaochen Yang, Zhanyu Ma +1

Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images. One main solution to few…

cs.CV2021

SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes

Jiacheng Chen, Bin-Bin Gao, Zongqing Lu +3

Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metri…

cs.CV2021★ 22 cited

Towards Open-World Text-Guided Face Image Generation and Manipulation

Weihao Xia, Yujiu Yang, Jing-Hao Xue +1

The existing text-guided image synthesis methods can only produce limited quality results with at most \mbox{} resolution and the textual instructions are constrained…