97 citations · 847 across the 68 of their papers we have counts for
7 papers · 1 filter
Learning to Compose Dynamic Tree Structures for Visual Contexts
Kaihua Tang, Hanwang Zhang, Baoyuan Wu +2
We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A…
Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance
Zechun Liu, Wenhan Luo, Baoyuan Wu +3
In this paper, we study 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While efficient, the lacking of representational capabilit…
Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm
Zechun Liu, Baoyuan Wu, Wenhan Luo +3
In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While being efficient, the classification accuracy of t…
Multi-label Learning with Missing Labels using Mixed Dependency Graphs
Baoyuan Wu, Fan Jia, Wei Liu +2
This work focuses on the problem of multi-label learning with missing labels (MLML), which aims to label each test instance with multiple class labels given training instances that…
Tagging like Humans: Diverse and Distinct Image Annotation
Baoyuan Wu, Weidong Chen, Peng Sun +3
In this work we propose a new automatic image annotation model, dubbed {\bf diverse and distinct image annotation} (D2IA). The generative model D2IA is inspired by the ensemble of…
CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF
Linchao Bao, Baoyuan Wu, Wei Liu
This paper addresses the problem of video object segmentation, where the initial object mask is given in the first frame of an input video. We propose a novel spatio-temporal Marko…
A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training
Tim Tsz-Kit Lau, Jinshan Zeng, Baoyuan Wu +1
Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most…