107 citations · 380 across the 45 of their papers we have counts for
9 papers · 1 filter
Siamese Network with Interactive Transformer for Video Object Segmentation
Meng Lan, Jing Zhang, Fengxiang He +1
Semi-supervised video object segmentation (VOS) refers to segmenting the target object in remaining frames given its annotation in the first frame, which has been actively studied…
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Yue He, Chen Chen, Jing Zhang +4
Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) m…
Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer
Shiye Lei, Zhuozhuo Tu, Leszek Rutkowski +4
Bayesian neural networks (BNNs) have become a principal approach to alleviate overconfident predictions in deep learning, but they often suffer from scaling issues due to a large n…
Spectral Complexity-scaled Generalization Bound of Complex-valued Neural Networks
Haowen Chen, Fengxiang He, Shiye Lei +1
Complex-valued neural networks (CVNNs) have been widely applied to various fields, especially signal processing and image recognition. However, few works focus on the generalizatio…
Self-Ensembling GAN for Cross-Domain Semantic Segmentation
Yonghao Xu, Fengxiang He, Bo Du +2
Deep neural networks (DNNs) have greatly contributed to the performance gains in semantic segmentation. Nevertheless, training DNNs generally requires large amounts of pixel-level…
Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction
Yikai Wang, Fuchun Sun, Wenbing Huang +2
Multimodal fusion and multitask learning are two vital topics in machine learning. Despite the fruitful progress, existing methods for both problems are still brittle to the same c…
Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers
Wen Wang, Yang Cao, Jing Zhang +4
Detection transformers have recently shown promising object detection results and attracted increasing attention. However, how to develop effective domain adaptation techniques to…
Bayesian Inference Forgetting
Shaopeng Fu, Fengxiang He, Yue Xu +1
The right to be forgotten has been legislated in many countries but the enforcement in machine learning would cause unbearable costs: companies may need to delete whole models lear…
Neural networks behave as hash encoders: An empirical study
Fengxiang He, Shiye Lei, Jianmin Ji +1
The input space of a neural network with ReLU-like activations is partitioned into multiple linear regions, each corresponding to a specific activation pattern of the included ReLU…