539 citations · 843 across the 24 of their papers we have counts for
6 papers · 1 filter
HDNet: A Hierarchically Decoupled Network for Crowd Counting
Chenliang Gu, Changan Wang, Bin-Bin Gao +2
Recently, density map regression-based methods have dominated in crowd counting owing to their excellent fitting ability on density distribution. However, further improvement tends…
Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision
Jiawei Zhan, Jun Liu, Wei Tang +8
Multi-label image classification, which can be categorized into label-dependency and region-based methods, is a challenging problem due to the complex underlying object layouts. Al…
Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective
Jinxiang Lai, Siqian Yang, Guannan Jiang +9
Few-shot learning problem focuses on recognizing unseen classes given a few labeled images. In recent effort, more attention is paid to fine-grained feature embedding, ignoring the…
tSF: Transformer-based Semantic Filter for Few-Shot Learning
Jinxiang Lai, Siqian Yang, Wenlong Liu +6
Few-Shot Learning (FSL) alleviates the data shortage challenge via embedding discriminative target-aware features among plenty seen (base) and few unseen (novel) labeled samples. M…
How to Reduce Change Detection to Semantic Segmentation
Guo-Hua Wang, Bin-Bin Gao, Chengjie Wang
Change detection (CD) aims to identify changes that occur in an image pair taken different times. Prior methods devise specific networks from scratch to predict change masks in pix…
UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation
Jiashuo Fan, Bin Gao, Huan Jin +1
Deep neural networks (DNNs) have witnessed great successes in semantic segmentation, which requires a large number of labeled data for training. We present a novel learning framewo…