618 citations · 1.4k across the 19 of their papers we have counts for
19 papers
FastPillars: A Deployment-friendly Pillar-based 3D Detector
Sifan Zhou, Zhi Tian, Xiangxiang Chu +7
The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios. Existing BEV-based (i.e., Bird Eye View) detectors favor sparse convolution…
Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images
Zhi Tian, Xiangxiang Chu, Xiaoming Wang +2
We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant metho…
Adaptive-Gravity: A Defense Against Adversarial Samples
Ali Mirzaeian, Zhi Tian, Sai Manoj P D +4
This paper presents a novel model training solution, denoted as Adaptive-Gravity, for enhancing the robustness of deep neural network classifiers against adversarial examples. We c…
Poseur: Direct Human Pose Regression with Transformers
Weian Mao, Yongtao Ge, Chunhua Shen +4
We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transf…
NAS-FCOS: Efficient Search for Object Detection Architectures
Ning Wang, Yang Gao, Hao Chen +4
Neural Architecture Search (NAS) has shown great potential in effectively reducing manual effort in network design by automatically discovering optimal architectures. What is notew…
Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation
Bowen Zhang, Yifan Liu, Zhi Tian +1
Semantic segmentation requires per-pixel prediction for a given image. Typically, the output resolution of a segmentation network is severely reduced due to the downsampling operat…
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
Xiangxiang Chu, Zhi Tian, Yuqing Wang +5
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their s…
TFPose: Direct Human Pose Estimation with Transformers
Weian Mao, Yongtao Ge, Chunhua Shen +3
We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-…
Conditional Positional Encodings for Vision Transformers
Xiangxiang Chu, Zhi Tian, Bo Zhang +2
We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of…
Instance and Panoptic Segmentation Using Conditional Convolutions
Zhi Tian, Bowen Zhang, Hao Chen +1
We propose a simple yet effective framework for instance and panoptic segmentation, termed CondInst (conditional convolutions for instance and panoptic segmentation). In the litera…
BoxInst: High-Performance Instance Segmentation with Box Annotations
Zhi Tian, Chunhua Shen, Xinlong Wang +1
We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training. While this setting has been studied in the l…
Unifying Instance and Panoptic Segmentation with Dynamic Rank-1 Convolutions
Hao Chen, Chunhua Shen, Zhi Tian
Recently, fully-convolutional one-stage networks have shown superior performance comparing to two-stage frameworks for instance segmentation as typically they can generate higher-q…
FCOS: A simple and strong anchor-free object detector
Zhi Tian, Chunhua Shen, Hao Chen +1
In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications. Recently one-stage met…
DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
Wei Yin, Xinlong Wang, Chunhua Shen +5
We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shap…
Mask Encoding for Single Shot Instance Segmentation
Rufeng Zhang, Zhi Tian, Chunhua Shen +2
To date, instance segmentation is dominated by twostage methods, as pioneered by Mask R-CNN. In contrast, one-stage alternatives cannot compete with Mask R-CNN in mask AP, mainly d…
Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
Tong He, Dong Gong, Zhi Tian +1
3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding. Due to the complex structure, point sets are distributed off balance and di…
BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
Hao Chen, Kunyang Sun, Zhi Tian +3
Instance segmentation is one of the fundamental vision tasks. Recently, fully convolutional instance segmentation methods have drawn much attention as they are often simpler and mo…
DirectPose: Direct End-to-End Multi-Person Pose Estimation
Zhi Tian, Hao Chen, Chunhua Shen
We propose the first direct end-to-end multi-person pose estimation framework, termed DirectPose. Inspired by recent anchor-free object detectors, which directly regress the two co…
Convolutional Character Networks
Linjie Xing, Zhi Tian, Weilin Huang +1
Recent progress has been made on developing a unified framework for joint text detection and recognition in natural images, but existing joint models were mostly built on two-stage…