Chi Zhang

We present CANet, a class-agnostic segmentation network that performs few-shot segmentation on new classes with only a few annotated images available. Expand

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

We address the few-shot classification task from a new perspective of optimal matching between image regions. Expand

In this paper, we propose a cross-reference network (CRNet) for few-shot segmentation. Expand

This paper presents a novel efficient gaze based text input method, which has the advantage of low cost and robustness. Expand

In this paper, we propose a novel method, Conditional Gaussian Distribution Learning (CGDL), for open set recognition. Expand

We propose to learn a structured fully connected layer that can directly classify dense image representations with the proposed EMD. Expand

We present the Compositional Prototype Network that can undertake point cloud segmentation with only a few labeled training data. Expand

We present CycleSegNet, a novel framework for the co-segmentation task which achieves new state-of-the-art performance. Expand

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