21 citations · 45 across the 7 of their papers we have counts for
7 papers
Phase Matching for Out-of-Distribution Generalization
Chengming Hu, Yeqian Du, Rui Wang +2
The Fourier transform, an explicit decomposition method for visual signals, has been employed to explain the out-of-distribution generalization behaviors of Deep Neural Networks (D…
BiSVP: Building Footprint Extraction via Bidirectional Serialized Vertex Prediction
Mingming Zhang, Ye Du, Zhenghui Hu +2
Extracting building footprints from remote sensing images has been attracting extensive attention recently. Dominant approaches address this challenging problem by generating vecto…
Learning from Future: A Novel Self-Training Framework for Semantic Segmentation
Ye Du, Yujun Shen, Haochen Wang +6
Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and…
A Complementary Joint Training Approach Using Unpaired Speech and Text for Low-Resource Automatic Speech Recognition
Ye-Qian Du, Jie Zhang, Qiu-Shi Zhu +4
Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or langu…
Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast
Ye Du, Zehua Fu, Qingjie Liu +1
Though image-level weakly supervised semantic segmentation (WSSS) has achieved great progress with Class Activation Maps (CAMs) as the cornerstone, the large supervision gap betwee…
Visual Grounding with Transformers
Ye Du, Zehua Fu, Qingjie Liu +1
In this paper, we propose a transformer based approach for visual grounding. Unlike previous proposal-and-rank frameworks that rely heavily on pretrained object detectors or propos…
ARM: A Confidence-Based Adversarial Reweighting Module for Coarse Semantic Segmentation
Jingchao Liu, Ye Du, Zehua Fu +2
Coarsely-labeled semantic segmentation annotations are easy to obtain, but therefore bear the risk of losing edge details and introducing background pixels. Impeded by the inherent…