activity
20182022
most citedCFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation

48 citations · 65 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CV202216 cited

Breaking Bad: A Dataset for Geometric Fracture and Reassembly

Silvia Sellán, Yun-Chun Chen, Ziyi Wu +2

We introduce Breaking Bad, a large-scale dataset of fractured objects. Our dataset consists of over one million fractured objects simulated from ten thousand base models. The fract…

cs.CV20221 cited

Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning

Pengxiang Yan, Ziyi Wu, Mengmeng Liu +3

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the…

cs.CV2021

Instance Similarity Learning for Unsupervised Feature Representation

Ziwei Wang, Yunsong Wang, Ziyi Wu +2

In this paper, we propose an instance similarity learning (ISL) method for unsupervised feature representation. Conventional methods assign close instance pairs in the feature spac…

cs.CL2021

RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge

Bill Yuchen Lin, Ziyi Wu, Yichi Yang +2

Question: I have five fingers but I am not alive. What am I? Answer: a glove. Answering such a riddle-style question is a challenging cognitive process, in that it requires complex…

cs.CV2020

IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration

Ziyi Wu, Yueqi Duan, He Wang +2

Point cloud is an important 3D data representation widely used in many essential applications. Leveraging deep neural networks, recent works have shown great success in processing…

cs.CV2020

BiDet: An Efficient Binarized Object Detector

Ziwei Wang, Ziyi Wu, Jiwen Lu +1

In this paper, we propose a binarized neural network learning method called BiDet for efficient object detection. Conventional network binarization methods directly quantize the we…