Search Results for author: Xiaojuan Qi

Found 55 papers, 30 papers with code

Memory Selection Network for Video Propagation

no code implementations ECCV 2020 Ruizheng Wu, Huaijia Lin, Xiaojuan Qi, Jiaya Jia

Video propagation is a fundamental problem in video processing where guidance frame predictions are propagated to guide predictions of the target frame.

Colorization Frame +4

CN: Channel Normalization For Point Cloud Recognition

no code implementations ECCV 2020 Zetong Yang, Yanan sun, Shu Liu, Xiaojuan Qi, Jiaya Jia

In 3D recognition, to fuse multi-scale structure information, existing methods apply hierarchical frameworks stacked by multiple fusion layers for integrating current relative locations with structure information from the previous level.

Video Demoireing with Relation-Based Temporal Consistency

no code implementations6 Apr 2022 Peng Dai, Xin Yu, Lan Ma, Baoheng Zhang, Jia Li, Wenbo Li, Jiajun Shen, Xiaojuan Qi

Moire patterns, appearing as color distortions, severely degrade image and video qualities when filming a screen with digital cameras.


MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator

no code implementations29 Mar 2022 Chang Liu, Xiaoyan Qian, Xiaojuan Qi, Edmund Y. Lam, Siew-Chong Tan, Ngai Wong

While a few previous studies tried to automatically generate 3D bounding boxes from weak labels such as 2D boxes, the quality is sub-optimal compared to human annotators.

Object Detection

Stratified Transformer for 3D Point Cloud Segmentation

2 code implementations28 Mar 2022 Xin Lai, Jianhui Liu, Li Jiang, LiWei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia

In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance.

Point Cloud Segmentation Semantic Segmentation

Towards Implicit Text-Guided 3D Shape Generation

1 code implementation28 Mar 2022 Zhengzhe Liu, Yi Wang, Xiaojuan Qi, Chi-Wing Fu

In this work, we explore the challenging task of generating 3D shapes from text.

3D Shape Generation

HINT: Hierarchical Neuron Concept Explainer

1 code implementation27 Mar 2022 Andong Wang, Wei-Ning Lee, Xiaojuan Qi

To this end, we propose HIerarchical Neuron concepT explainer (HINT) to effectively build bidirectional associations between neurons and hierarchical concepts in a low-cost and scalable manner.

Weakly-Supervised Object Localization

Progressive End-to-End Object Detection in Crowded Scenes

1 code implementation15 Mar 2022 Anlin Zheng, Yuang Zhang, Xiangyu Zhang, Xiaojuan Qi, Jian Sun

Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes.

Object Detection

Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking

2 code implementations CVPR 2020 Jin Gao, Yan Lu, Xiaojuan Qi, Yutong Kou, Bing Li, Liang Li, Shan Yu, Weiming Hu

In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot online adaptation without requiring offline training.

Continual Learning One-Shot Learning +2

Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation

no code implementations16 Dec 2021 Yi Zhou, HUI ZHANG, Hana Lee, Shuyang Sun, Pingjun Li, Yangguang Zhu, ByungIn Yoo, Xiaojuan Qi, Jae-Joon Han

We encode all panoptic entities in a video, including both foreground instances and background semantics, with a unified representation called panoptic slots.

Panoptic Segmentation Representation Learning

Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision

1 code implementation17 Aug 2021 Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Yukang Chen, Lu Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia

In particular, Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.

Panoptic Segmentation Weakly-supervised panoptic segmentation

ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection

no code implementations15 Aug 2021 Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi

These specific designs enable the detector to be trained on meticulously refined pseudo labeled target data with denoised training signals, and thus effectively facilitate adapting an object detector to a target domain without requiring annotations.

3D Object Detection Data Augmentation +2

Multilevel Knowledge Transfer for Cross-Domain Object Detection

no code implementations2 Aug 2021 Botos Csaba, Xiaojuan Qi, Arslan Chaudhry, Puneet Dokania, Philip Torr

The key ingredients to our approach are -- (a) mapping the source to the target domain on pixel-level; (b) training a teacher network on the mapped source and the unannotated target domain using adversarial feature alignment; and (c) finally training a student network using the pseudo-labels obtained from the teacher.

Object Detection Transfer Learning

Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation

1 code implementation ICCV 2021 Ruifei He, Jihan Yang, Xiaojuan Qi

In this paper, we present a simple and yet effective Distribution Alignment and Random Sampling (DARS) method to produce unbiased pseudo labels that match the true class distribution estimated from the labeled data.

Data Augmentation Semi-Supervised Semantic Segmentation

3D-to-2D Distillation for Indoor Scene Parsing

1 code implementation CVPR 2021 Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu

First, we distill 3D knowledge from a pretrained 3D network to supervise a 2D network to learn simulated 3D features from 2D features during the training, so the 2D network can infer without requiring 3D data.

Scene Parsing Semantic Parsing +1

One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation

2 code implementations CVPR 2021 Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu

Point cloud semantic segmentation often requires largescale annotated training data, but clearly, point-wise labels are too tedious to prepare.

3D Semantic Segmentation

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

1 code implementation CVPR 2021 Mutian Xu, Runyu Ding, Hengshuang Zhao, Xiaojuan Qi

The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point positions through ScoreNet.

3D Point Cloud Classification

AET-EFN: A Versatile Design for Static and Dynamic Event-Based Vision

no code implementations22 Mar 2021 Chang Liu, Xiaojuan Qi, Edmund Lam, Ngai Wong

The neuromorphic event cameras, which capture the optical changes of a scene, have drawn increasing attention due to their high speed and low power consumption.

Event-based vision Frame

ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection

1 code implementation CVPR 2021 Jihan Yang, Shaoshuai Shi, Zhe Wang, Hongsheng Li, Xiaojuan Qi

Then, the detector is iteratively improved on the target domain by alternatively conducting two steps, which are the pseudo label updating with the developed quality-aware triplet memory bank and the model training with curriculum data augmentation.

3D Object Detection Data Augmentation +1

Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud

1 code implementation20 Dec 2020 Mutian Xu, Junhao Zhang, Zhipeng Zhou, Mingye Xu, Xiaojuan Qi, Yu Qiao

GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components.

3D Object Classification 3D Part Segmentation

GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation

2 code implementations13 Dec 2020 Xiaojuan Qi, Zhengzhe Liu, Renjie Liao, Philip H. S. Torr, Raquel Urtasun, Jiaya Jia

Note that GeoNet++ is generic and can be used in other depth/normal prediction frameworks to improve the quality of 3D reconstruction and pixel-wise accuracy of depth and surface normals.

3D Reconstruction Depth Estimation

Fully Convolutional Networks for Panoptic Segmentation

5 code implementations CVPR 2021 Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia

In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN.

 Ranked #1 on Panoptic Segmentation on Cityscapes val (PQst metric)

Panoptic Segmentation

Object-aware Feature Aggregation for Video Object Detection

no code implementations23 Oct 2020 Qichuan Geng, Hong Zhang, Na Jiang, Xiaojuan Qi, Liangjun Zhang, Zhong Zhou

As a consequence, augmenting features with such prior knowledge can effectively improve the classification and localization performance.

Object Recognition Video Object Detection

Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation

1 code implementation NeurIPS 2020 Bowen Li, Xiaojuan Qi, Philip H. S. Torr, Thomas Lukasiewicz

To achieve this, a new word-level discriminator is proposed, which provides the generator with fine-grained training feedback at word-level, to facilitate training a lightweight generator that has a small number of parameters, but can still correctly focus on specific visual attributes of an image, and then edit them without affecting other contents that are not described in the text.

 Ranked #1 on Text-to-Image Generation on CUB (FID metric, using extra training data)

Image Manipulation Text-to-Image Generation

Edge Guided GANs with Semantic Preserving for Semantic Image Synthesis

1 code implementation31 Mar 2020 Hao Tang, Xiaojuan Qi, Dan Xu, Philip H. S. Torr, Nicu Sebe

To tackle the first challenge, we propose to use the edge as an intermediate representation which is further adopted to guide image generation via a proposed attention guided edge transfer module.

Image Generation

Image-to-Image Translation with Text Guidance

no code implementations12 Feb 2020 Bowen Li, Xiaojuan Qi, Philip H. S. Torr, Thomas Lukasiewicz

The goal of this paper is to embed controllable factors, i. e., natural language descriptions, into image-to-image translation with generative adversarial networks, which allows text descriptions to determine the visual attributes of synthetic images.

Image-to-Image Translation Part-Of-Speech Tagging +1

Global Texture Enhancement for Fake Face Detection in the Wild

no code implementations CVPR 2020 Zhengzhe Liu, Xiaojuan Qi, Philip Torr

In this paper, we conduct an empirical study on fake/real faces, and have two important observations: firstly, the texture of fake faces is substantially different from real ones; secondly, global texture statistics are more robust to image editing and transferable to fake faces from different GANs and datasets.

Face Detection Fake Image Detection

Gated Path Selection Network for Semantic Segmentation

no code implementations19 Jan 2020 Qichuan Geng, Hong Zhang, Xiaojuan Qi, Ruigang Yang, Zhong Zhou, Gao Huang

Semantic segmentation is a challenging task that needs to handle large scale variations, deformations and different viewpoints.

Semantic Segmentation

Unifying Training and Inference for Panoptic Segmentation

no code implementations CVPR 2020 Qizhu Li, Xiaojuan Qi, Philip H. S. Torr

This panoptic submodule gives rise to a novel propagation mechanism for panoptic logits and enables the network to output a coherent panoptic segmentation map for both "stuff" and "thing" classes, without any post-processing.

Panoptic Segmentation

Few-shot Action Recognition with Permutation-invariant Attention

no code implementations ECCV 2020 Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li, Philip H. S. Torr, Piotr Koniusz

Such encoded blocks are aggregated by permutation-invariant pooling to make our approach robust to varying action lengths and long-range temporal dependencies whose patterns are unlikely to repeat even in clips of the same class.

Few Shot Action Recognition Few-Shot Learning +1

An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation

no code implementations18 Dec 2019 Jihan Yang, Ruijia Xu, Ruiyu Li, Xiaojuan Qi, Xiaoyong Shen, Guanbin Li, Liang Lin

In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations.

Semantic Segmentation Unsupervised Domain Adaptation

ManiGAN: Text-Guided Image Manipulation

3 code implementations12 Dec 2019 Bowen Li, Xiaojuan Qi, Thomas Lukasiewicz, Philip H. S. Torr

The goal of our paper is to semantically edit parts of an image matching a given text that describes desired attributes (e. g., texture, colour, and background), while preserving other contents that are irrelevant to the text.

 Ranked #1 on Text-to-Image Generation on CUB (using extra training data)

Image Manipulation Text-to-Image Generation

Domain-invariant Stereo Matching Networks

1 code implementation ECCV 2020 Feihu Zhang, Xiaojuan Qi, Ruigang Yang, Victor Prisacariu, Benjamin Wah, Philip Torr

State-of-the-art stereo matching networks have difficulties in generalizing to new unseen environments due to significant domain differences, such as color, illumination, contrast, and texture.

Stereo Matching

Controllable Text-to-Image Generation

2 code implementations NeurIPS 2019 Bowen Li, Xiaojuan Qi, Thomas Lukasiewicz, Philip H. S. Torr

In this paper, we propose a novel controllable text-to-image generative adversarial network (ControlGAN), which can effectively synthesise high-quality images and also control parts of the image generation according to natural language descriptions.

Text to image generation Text-to-Image Generation

Improved Techniques for Training Adaptive Deep Networks

1 code implementation ICCV 2019 Hao Li, Hong Zhang, Xiaojuan Qi, Ruigang Yang, Gao Huang

Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time.

Knowledge Distillation

Human Pose Estimation with Spatial Contextual Information

no code implementations7 Jan 2019 Hong Zhang, Hao Ouyang, Shu Liu, Xiaojuan Qi, Xiaoyong Shen, Ruigang Yang, Jiaya Jia

With this principle, we present two conceptually simple and yet computational efficient modules, namely Cascade Prediction Fusion (CPF) and Pose Graph Neural Network (PGNN), to exploit underlying contextual information.

Pose Estimation

GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation

1 code implementation CVPR 2018 Xiaojuan Qi, Renjie Liao, Zhengzhe Liu, Raquel Urtasun, Jiaya Jia

In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and surface normal maps from a single image.

Depth Estimation

Semantically Consistent Image Completion with Fine-grained Details

no code implementations26 Nov 2017 Pengpeng Liu, Xiaojuan Qi, Pinjia He, Yikang Li, Michael R. Lyu, Irwin King

Image completion has achieved significant progress due to advances in generative adversarial networks (GANs).

Image Inpainting

3D Graph Neural Networks for RGBD Semantic Segmentation

2 code implementations ICCV 2017 Xiaojuan Qi, Renjie Liao, Jiaya Jia, Sanja Fidler, Raquel Urtasun

Each node in the graph corresponds to a set of points and is associated with a hidden representation vector initialized with an appearance feature extracted by a unary CNN from 2D images.

Semantic Segmentation

H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes

1 code implementation21 Sep 2017 Xiaomeng Li, Hao Chen, Xiaojuan Qi, Qi Dou, Chi-Wing Fu, Pheng Ann Heng

Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.

Automatic Liver And Tumor Segmentation Lesion Segmentation +2

Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation

no code implementations CVPR 2016 Shu Liu, Xiaojuan Qi, Jianping Shi, Hong Zhang, Jiaya Jia

Aiming at simultaneous detection and segmentation (SDS), we propose a proposal-free framework, which detect and segment object instances via mid-level patches.

Object Proposal Generation

DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation

no code implementations CVPR 2016 Hao Chen, Xiaojuan Qi, Lequan Yu, Pheng-Ann Heng

The morphology of glands has been used routinely by pathologists to assess the malignancy degree of adenocarcinomas.

Multi-Task Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.