401 citations · 1.6k across the 64 of their papers we have counts for
6 papers · 1 filter
Single-Shot Object Detection with Enriched Semantics
Zhishuai Zhang, Siyuan Qiao, Cihang Xie +3
We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within…
Visual Concepts and Compositional Voting
Jianyu Wang, Zhishuai Zhang, Cihang Xie +5
It is very attractive to formulate vision in terms of pattern theory \cite{Mumford2010pattern}, where patterns are defined hierarchically by compositions of elementary building blo…
Mitigating Adversarial Effects Through Randomization
Cihang Xie, Jianyu Wang, Zhishuai Zhang +2
Convolutional neural networks have demonstrated high accuracy on various tasks in recent years. However, they are extremely vulnerable to adversarial examples. For example, imperce…
DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion
Zhishuai Zhang, Cihang Xie, Jianyu Wang +2
In this paper, we study the task of detecting semantic parts of an object, e.g., a wheel of a car, under partial occlusion. We propose that all models should be trained without see…
Detecting Semantic Parts on Partially Occluded Objects
Jianyu Wang, Cihang Xie, Zhishuai Zhang +3
In this paper, we address the task of detecting semantic parts on partially occluded objects. We consider a scenario where the model is trained using non-occluded images but tested…
Adversarial Examples for Semantic Segmentation and Object Detection
Cihang Xie, Jianyu Wang, Zhishuai Zhang +3
It has been well demonstrated that adversarial examples, i.e., natural images with visually imperceptible perturbations added, generally exist for deep networks to fail on image cl…