• Publications
  • Influence
CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning
TLDR
We present CANet, a class-agnostic segmentation network that performs few-shot segmentation on new classes with only a few annotated images available. Expand
  • 70
  • 24
  • PDF
Pyramid Graph Networks With Connection Attentions for Region-Based One-Shot Semantic Segmentation
TLDR
In this paper, we propose to model structured segmentation data with graphs and apply attentive graph reasoning to propagate label information from support data to query data. Expand
  • 36
  • 10
  • PDF
DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover’s Distance and Structured Classifiers
TLDR
We address the few-shot classification task from a new perspective of optimal matching between image regions. Expand
  • 36
  • 4
  • PDF
CRNet: Cross-Reference Networks for Few-Shot Segmentation
TLDR
In this paper, we propose a cross-reference network (CRNet) for few-shot segmentation. Expand
  • 12
  • 2
  • PDF
Efficient eye typing with 9-direction gaze estimation
TLDR
This paper presents a novel efficient gaze based text input method, which has the advantage of low cost and robustness. Expand
  • 17
  • 1
  • PDF
Conditional Gaussian Distribution Learning for Open Set Recognition
TLDR
In this paper, we propose a novel method, Conditional Gaussian Distribution Learning (CGDL), for open set recognition. Expand
  • 9
  • 1
  • PDF
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
TLDR
We propose to learn a structured fully connected layer that can directly classify dense image representations with the proposed EMD. Expand
  • 3
  • PDF
Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation
TLDR
We present the Compositional Prototype Network that can undertake point cloud segmentation with only a few labeled training data. Expand
  • 1
  • PDF
CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence
TLDR
We present CycleSegNet, a novel framework for the co-segmentation task which achieves new state-of-the-art performance. Expand
Weakly Supervised Segmentation with Maximum Bipartite Graph Matching
TLDR
In the weakly supervised segmentation task with only image-level labels, a common step in many existing algorithms is first to locate the image regions corresponding to each existing class with the Class Activation Maps, and then generate the pseudo ground truth masks based on the CAMs to train a segmentation network in the fully supervised manner. Expand
  • 1