Search Results for author: Kui Jia

Found 110 papers, 66 papers with code

SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation

1 code implementation27 Nov 2023 Jiehong Lin, Lihua Liu, Dekun Lu, Kui Jia

Zero-shot 6D object pose estimation involves the detection of novel objects with their 6D poses in cluttered scenes, presenting significant challenges for model generalizability.

6D Pose Estimation using RGB Instance Segmentation +3

GS-IR: 3D Gaussian Splatting for Inverse Rendering

1 code implementation26 Nov 2023 Zhihao Liang, Qi Zhang, Ying Feng, Ying Shan, Kui Jia

We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results.

Inverse Rendering Novel View Synthesis

Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization

1 code implementation26 Sep 2023 Yongyi Su, Xun Xu, Kui Jia

Test-Time Adaptation aims to adapt source domain model to testing data at inference stage with success demonstrated in adapting to unseen corruptions.


PAI-Diffusion: Constructing and Serving a Family of Open Chinese Diffusion Models for Text-to-image Synthesis on the Cloud

no code implementations11 Sep 2023 Chengyu Wang, Zhongjie Duan, Bingyan Liu, Xinyi Zou, Cen Chen, Kui Jia, Jun Huang

Text-to-image synthesis for the Chinese language poses unique challenges due to its large vocabulary size, and intricate character relationships.

Image Generation Style Transfer

On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion

1 code implementation ICCV 2023 Yushu Li, Xun Xu, Yongyi Su, Kui Jia

Existing approaches often focus on improving test-time training performance under well-curated target domain data.


VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations

1 code implementation ICCV 2023 Jiehong Lin, Zewei Wei, Yabin Zhang, Kui Jia

We apply the proposed VI-Net to the challenging task of category-level 6D object pose estimation for predicting the poses of unknown objects without available CAD models; experiments on the benchmarking datasets confirm the efficacy of our method, which outperforms the existing ones with a large margin in the regime of high precision.

6D Pose Estimation using RGB Benchmarking +1

ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden States

1 code implementation30 May 2023 KangJun Liu, Ke Chen, Lihua Guo, YaoWei Wang, Kui Jia

Inspired by good robustness of alternative dropout strategies against over-fitting on limited patterns of training samples, this paper introduces a novel concept of ShuffleMix -- Shuffle of Mixed hidden features, which can be interpreted as a kind of dropout operation in feature space.

Benchmarking Data Augmentation +1

Improving Deep Representation Learning via Auxiliary Learnable Target Coding

1 code implementation30 May 2023 KangJun Liu, Ke Chen, YaoWei Wang, Kui Jia

Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks.

Representation Learning Retrieval

Universal Domain Adaptation from Foundation Models: A Baseline Study

1 code implementation18 May 2023 Bin Deng, Kui Jia

We hope that our investigation and the proposed simple framework can serve as a strong baseline to facilitate future studies in this field.

Universal Domain Adaptation

Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose

1 code implementation18 May 2023 Yichen Zhang, Jiehong Lin, Ke Chen, Zelin Xu, YaoWei Wang, Kui Jia

Domain gap between synthetic and real data in visual regression (e. g. 6D pose estimation) is bridged in this paper via global feature alignment and local refinement on the coarse classification of discretized anchor classes in target space, which imposes a piece-wise target manifold regularization into domain-invariant representation learning.

6D Pose Estimation regression +2

Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training

no code implementations20 Mar 2023 Yongyi Su, Xun Xu, Tianrui Li, Kui Jia

Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available, and instant inference on the target domain is required.

Benchmarking Clustering +1

A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation

1 code implementation CVPR 2023 Hui Tang, Kui Jia

Moreover, we use the simulation-to-reality adaptation as a downstream task for comparing the transferability between synthetic and real data when used for pre-training, which demonstrates that synthetic data pre-training is also promising to improve real test results.

Domain Adaptation Image Classification

Unsupervised Domain Adaptation via Distilled Discriminative Clustering

1 code implementation23 Feb 2023 Hui Tang, YaoWei Wang, Kui Jia

Differently, motivated by the fundamental assumption for domain adaptability, we re-cast the domain adaptation problem as discriminative clustering of target data, given strong privileged information provided by the closely related, labeled source data.

Clustering Unsupervised Domain Adaptation

Adversarial Style Augmentation for Domain Generalization

no code implementations30 Jan 2023 Yabin Zhang, Bin Deng, Ruihuang Li, Kui Jia, Lei Zhang

By updating the model against the adversarial statistics perturbation during training, we allow the model to explore the worst-case domain and hence improve its generalization performance.

Domain Generalization Retrieval

RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models

no code implementations CVPR 2023 Jiabao Lei, Jiapeng Tang, Kui Jia

More specifically, we maintain an intermediate surface mesh used for rendering new RGBD views, which subsequently becomes complete by an inpainting network; each rendered RGBD view is later back-projected as a partial surface and is supplemented into the intermediate mesh.

Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning

1 code implementation13 Nov 2022 Yabin Zhang, Jiehong Lin, Ruihuang Li, Kui Jia, Lei Zhang

We also validate the effectiveness of affine transformation corruption with the Transformer backbones, where we decompose the reconstruction of the complete point cloud into the reconstructions of detailed local patches and rough global shape, alleviating the position leakage problem in the reconstruction.

3D Object Detection Denoising +2

TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition

1 code implementation20 Oct 2022 Yongwei Chen, Rui Chen, Jiabao Lei, Yabin Zhang, Kui Jia

Creation of 3D content by stylization is a promising yet challenging problem in computer vision and graphics research.

Style Transfer

DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation

1 code implementation11 Oct 2022 Hongyang Li, Jiehong Lin, Kui Jia

Establishment of point correspondence between camera and object coordinate systems is a promising way to solve 6D object poses.

6D Pose Estimation 6D Pose Estimation using RGB +1

Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization

1 code implementation16 Aug 2022 Bin Deng, Kui Jia

First, we show that the key assumption of support overlap of invariant features used in IB-IRM is strong for the guarantee of OOD generalization and it is still possible to achieve the optimal solution without this assumption.

counterfactual Counterfactual Inference +1

Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization

1 code implementation3 Aug 2022 KangJun Liu, Ke Chen, Kui Jia

Such target coding schemes are less flexible to model inter-class correlation and are sensitive to sparse and imbalanced data distribution as well.

Classification Data Augmentation +2

Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks

1 code implementation12 Jul 2022 Jiehong Lin, Zewei Wei, Changxing Ding, Kui Jia

It is difficult to precisely annotate object instances and their semantics in 3D space, and as such, synthetic data are extensively used for these tasks, e. g., category-level 6D object pose and size estimation.

6D Pose Estimation Unsupervised Domain Adaptation

Masked Surfel Prediction for Self-Supervised Point Cloud Learning

1 code implementation7 Jul 2022 Yabin Zhang, Jiehong Lin, Chenhang He, Yongwei Chen, Kui Jia, Lei Zhang

In this work, we make the first attempt, to the best of our knowledge, to consider the local geometry information explicitly into the masked auto-encoding, and propose a novel Masked Surfel Prediction (MaskSurf) method.

Point cloud reconstruction Self-Supervised Learning

Style Interleaved Learning for Generalizable Person Re-identification

1 code implementation7 Jul 2022 Wentao Tan, Changxing Ding, Pengfei Wang, Mingming Gong, Kui Jia

This common practice causes the model to overfit to existing feature styles in the source domain, resulting in sub-optimal generalization ability on target domains.

Domain Generalization Generalizable Person Re-identification +1

Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering

1 code implementation6 Jun 2022 Yongyi Su, Xun Xu, Kui Jia

Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available and instant inference on target domain is required.

Benchmarking Clustering +2

BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation

1 code implementation7 May 2022 Zelin Xu, Yichen Zhang, Ke Chen, Kui Jia

Inspired by the success of point-pair features, the goal of this paper is to recover the 6D pose of an object instance segmented from RGB-D images by locally matching pairs of oriented points between the model and camera space.

6D Pose Estimation Benchmarking +1

Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning

no code implementations6 May 2022 Yongyi Su, Xun Xu, Kui Jia

Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning.

Point Cloud Segmentation Segmentation +2

Surface Reconstruction from Point Clouds: A Survey and a Benchmark

no code implementations5 May 2022 Zhangjin Huang, Yuxin Wen, ZiHao Wang, Jinjuan Ren, Kui Jia

For example, while deep learning methods are increasingly popular, our systematic studies suggest that, surprisingly, a few classical methods perform even better in terms of both robustness and generalization; our studies also suggest that the practical challenges of misalignment of point sets from multi-view scanning, missing of surface points, and point outliers remain unsolved by all the existing surface reconstruction methods.

Benchmarking Surface Reconstruction

VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention

1 code implementation CVPR 2022 Shengheng Deng, Zhihao Liang, Lin Sun, Kui Jia

These multi-view methods either refine the proposals predicted from single view via fused features, or fuse the features without considering the global spatial context; their performance is limited consequently.

3D Object Detection Autonomous Driving +1

Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

1 code implementation CVPR 2022 Yabin Zhang, Minghan Li, Ruihuang Li, Kui Jia, Lei Zhang

In this work, we, for the first time to our best knowledge, propose to perform Exact Feature Distribution Matching (EFDM) by exactly matching the empirical Cumulative Distribution Functions (eCDFs) of image features, which could be implemented by applying the Exact Histogram Matching (EHM) in the image feature space.

Domain Generalization Style Transfer

Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap

1 code implementation8 Mar 2022 Yongwei Chen, ZiHao Wang, Longkun Zou, Ke Chen, Kui Jia

Such a challenge of Simulation-to-Reality (Sim2Real) domain gap could be mitigated via learning algorithms of domain adaptation; however, we argue that generation of synthetic point clouds via more physically realistic rendering is a powerful alternative, as systematic non-uniform noise patterns can be captured.

Benchmarking Point Cloud Classification +1

Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning

no code implementations CVPR 2022 Hui Tang, Kui Jia

To answer these problems, we propose a novel Taylor expansion inspired filtration (TEIF) framework, which admits the samples of moderate confidence with similar feature or gradient to the respective one averaged over the labeled and highly confident unlabeled data.

Model Optimization Semi-Supervised Image Classification

Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space

1 code implementation NeurIPS 2021 Jiehong Lin, Hongyang Li, Ke Chen, Jiangbo Lu, Kui Jia

In this paper, we propose a novel design of Sparse Steerable Convolution (SS-Conv) to address the shortcoming; SS-Conv greatly accelerates steerable convolution with sparse tensors, while strictly preserving the property of SE(3)-equivariance.

6D Pose Estimation Pose Tracking

Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification

1 code implementation22 Aug 2021 Pengfei Wang, Changxing Ding, Wentao Tan, Mingming Gong, Kui Jia, DaCheng Tao

In particular, the performance of our unsupervised UCF method in the MSMT17$\to$Market1501 task is better than that of the fully supervised setting on Market1501.


Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds

1 code implementation20 Aug 2021 Longkun Zou, Hui Tang, Ke Chen, Kui Jia

The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets.

Point Cloud Classification Representation Learning +1

Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks

1 code implementation ICCV 2021 Zhihao Liang, Zhihao LI, Songcen Xu, Mingkui Tan, Kui Jia

State-of-the-art methods largely rely on a general pipeline that first learns point-wise features discriminative at semantic and instance levels, followed by a separate step of point grouping for proposing object instances.

3D Instance Segmentation Scene Understanding +1

Content-Aware Convolutional Neural Networks

1 code implementation30 Jun 2021 Yong Guo, Yaofo Chen, Mingkui Tan, Kui Jia, Jian Chen, Jingdong Wang

In practice, the convolutional operation on some of the windows (e. g., smooth windows that contain very similar pixels) can be very redundant and may introduce noises into the computation.

Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation

1 code implementation ICCV 2021 Zhuangwei Zhuang, Rong Li, Kui Jia, Qicheng Wang, Yuanqing Li, Mingkui Tan

In this work, we investigate a collaborative fusion scheme called perception-aware multi-sensor fusion (PMF) to exploit perceptual information from two modalities, namely, appearance information from RGB images and spatio-depth information from point clouds.

LIDAR Semantic Segmentation Scene Understanding +2

Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching

1 code implementation18 Jun 2021 Jiabao Lei, Kui Jia, Yi Ma

More specifically, we identify from the linear regions, partitioned by an MLP based implicit function, the analytic cells and analytic faces that are associated with the function's zero-level isosurface.

Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners

no code implementations1 Jun 2021 Yabin Zhang, Haojian Zhang, Bin Deng, Shuai Li, Kui Jia, Lei Zhang

Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques.

Unsupervised Domain Adaptation

SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks

1 code implementation ICCV 2021 Jiapeng Tang, Jiabao Lei, Dan Xu, Feiying Ma, Kui Jia, Lei Zhang

To this end, we propose to learn implicit surface reconstruction by sign-agnostic optimization of convolutional occupancy networks, to simultaneously achieve advanced scalability to large-scale scenes, generality to novel shapes, and applicability to raw scans in a unified framework.

Surface Reconstruction

On Universal Black-Box Domain Adaptation

1 code implementation10 Apr 2021 Bin Deng, Yabin Zhang, Hui Tang, Changxing Ding, Kui Jia

The great promise that UB$^2$DA makes, however, brings significant learning challenges, since domain adaptation can only rely on the predictions of unlabeled target data in a partially overlapped label space, by accessing the interface of source model.

Universal Domain Adaptation

DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency

1 code implementation ICCV 2021 Jiehong Lin, Zewei Wei, Zhihao LI, Songcen Xu, Kui Jia, Yuanqing Li

DualPoseNet stacks two parallel pose decoders on top of a shared pose encoder, where the implicit decoder predicts object poses with a working mechanism different from that of the explicit one; they thus impose complementary supervision on the training of pose encoder.

6D Pose Estimation using RGBD Pose Prediction

Vicinal and categorical domain adaptation

1 code implementation5 Mar 2021 Hui Tang, Kui Jia

Unsupervised domain adaptation aims to learn a task classifier that performs well on the unlabeled target domain, by utilizing the labeled source domain.

Unsupervised Domain Adaptation

Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach

no code implementations18 Jan 2021 Xian Shi, Xun Xu, Ke Chen, Lile Cai, Chuan Sheng Foo, Kui Jia

Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets.

Active Learning Benchmarking +3

Unsupervised Domain Adaptation of Black-Box Source Models

1 code implementation8 Jan 2021 Haojian Zhang, Yabin Zhang, Kui Jia, Lei Zhang

Unsupervised domain adaptation (UDA) aims to learn models for a target domain of unlabeled data by transferring knowledge from a labeled source domain.

Learning with noisy labels Unsupervised Domain Adaptation

Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds

1 code implementation ICCV 2021 Longkun Zou, Hui Tang, Ke Chen, Kui Jia

The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets.

Point Cloud Classification Representation Learning +1

Classification of Single-View Object Point Clouds

no code implementations18 Dec 2020 Zelin Xu, Ke Chen, KangJun Liu, Changxing Ding, YaoWei Wang, Kui Jia

By adapting existing ModelNet40 and ScanNet datasets to the single-view, partial setting, experiment results can verify the necessity of object pose estimation and superiority of our PAPNet to existing classifiers.

3D Object Classification 6D Pose Estimation using RGB +5

Learning Category-level Shape Saliency via Deep Implicit Surface Networks

no code implementations14 Dec 2020 Chaozheng Wu, Lin Sun, Xun Xu, Kui Jia

Given the large shape variations among different instances of a same category, we are formally interested in developing a quantity defined for individual points on a continuous object surface; the quantity specifies how individual surface points contribute to the formation of the shape as the category.

Point Cloud Classification Saliency Prediction

Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds

no code implementations CVPR 2021 Wenbin Zhao, Jiabao Lei, Yuxin Wen, JianGuo Zhang, Kui Jia

Motivated from a universal phenomenon that self-similar shape patterns of local surface patches repeat across the entire surface of an object, we aim to push forward the data-driven strategies and propose to learn a local implicit surface network for a shared, adaptive modeling of the entire surface for a direct surface reconstruction from raw point cloud; we also enhance the leveraging of surface self-similarities by improving correlations among the optimized latent codes of individual surface patches.

Surface Reconstruction

Deep Optimized Priors for 3D Shape Modeling and Reconstruction

no code implementations CVPR 2021 Mingyue Yang, Yuxin Wen, Weikai Chen, Yongwei Chen, Kui Jia

Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples.

3D Shape Modeling

Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering

2 code implementations8 Dec 2020 Hui Tang, Xiatian Zhu, Ke Chen, Kui Jia, C. L. Philip Chen

To address this issue, we are motivated by a UDA assumption of structural similarity across domains, and propose to directly uncover the intrinsic target discrimination via constrained clustering, where we constrain the clustering solutions using structural source regularization that hinges on the very same assumption.

Constrained Clustering Deep Clustering +3

Towards Understanding the Regularization of Adversarial Robustness on Neural Networks

no code implementations ICML 2020 Yuxin Wen, Shuai Li, Kui Jia

However, it is observed that such methods would lead to standard performance degradation, i. e., the degradation on natural examples.

Adversarial Robustness

A deep learning based interactive sketching system for fashion images design

no code implementations9 Oct 2020 Yao Li, Xianggang Yu, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu

In this work, we propose an interactive system to design diverse high-quality garment images from fashion sketches and the texture information.

Intrinsic Image Decomposition Texture Synthesis

Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps

2 code implementations NeurIPS 2020 Chaozheng Wu, Jian Chen, Qiaoyu Cao, Jianchi Zhang, Yunxin Tai, Lin Sun, Kui Jia

To test GPNet, we contribute a synthetic dataset of 6-DOF object grasps; evaluation is conducted using rule-based criteria, simulation test, and real test.


CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling

1 code implementation10 Sep 2020 Jiehong Lin, Xian Shi, Yuan Gao, Ke Chen, Kui Jia

Point set is arguably the most direct approximation of an object or scene surface, yet its practical acquisition often suffers from the shortcoming of being noisy, sparse, and possibly incomplete, which restricts its use for a high-quality surface recovery.

Point Set Upsampling

SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images

1 code implementation13 Aug 2020 Jiapeng Tang, Xiaoguang Han, Mingkui Tan, Xin Tong, Kui Jia

However, they all have their own drawbacks, and cannot properly reconstruct the surface shapes of complex topologies, arguably due to a lack of constraints on the topologicalstructures in their learning frameworks.

Surface Reconstruction

Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering

2 code implementations CVPR 2020 Hui Tang, Ke Chen, Kui Jia

To alleviate this risk, we are motivated by the assumption of structural domain similarity, and propose to directly uncover the intrinsic target discrimination via discriminative clustering of target data.

Clustering Deep Clustering +1

Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice

2 code implementations20 Feb 2020 Yabin Zhang, Bin Deng, Hui Tang, Lei Zhang, Kui Jia

By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains.

Domain Adaptation Multi-class Classification

Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks

1 code implementation ICML 2020 Jiabao Lei, Kui Jia

This paper studies a problem of learning surface mesh via implicit functions in an emerging field of deep learning surface reconstruction, where implicit functions are popularly implemented as multi-layer perceptrons (MLPs) with rectified linear units (ReLU).

Surface Reconstruction

Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors

no code implementations14 Jan 2020 Lulu Tang, Ke Chen, Chaozheng Wu, Yu Hong, Kui Jia, Zhi-Xin Yang

Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner.

W-PoseNet: Dense Correspondence Regularized Pixel Pair Pose Regression

no code implementations26 Dec 2019 Zelin Xu, Ke Chen, Kui Jia

Solving 6D pose estimation is non-trivial to cope with intrinsic appearance and shape variation and severe inter-object occlusion, and is made more challenging in light of extrinsic large illumination changes and low quality of the acquired data under an uncontrolled environment.

 Ranked #1 on 6D Pose Estimation using RGBD on LineMOD (Mean ADD-S metric)

6D Pose Estimation 6D Pose Estimation using RGBD +1

Cascading Convolutional Color Constancy

1 code implementation24 Dec 2019 Huanglin Yu, Ke Chen, Kaiqi Wang, Yanlin Qian, Zhao-Xiang Zhang, Kui Jia

Regressing the illumination of a scene from the representations of object appearances is popularly adopted in computational color constancy.

Color Constancy

Geometry-Aware Generation of Adversarial Point Clouds

2 code implementations24 Dec 2019 Yuxin Wen, Jiehong Lin, Ke Chen, C. L. Philip Chen, Kui Jia

Regularizing the targeted attack loss with our proposed geometry-aware objectives results in our proposed method, Geometry-Aware Adversarial Attack ($GeoA^3$).

Adversarial Attack Fairness

Discriminative Adversarial Domain Adaptation

2 code implementations27 Nov 2019 Hui Tang, Kui Jia

Based on an integrated category and domain classifier, DADA has a novel adversarial objective that encourages a mutually inhibitory relation between category and domain predictions for any input instance.

Unsupervised Domain Adaptation

Multi-marginal Wasserstein GAN

3 code implementations NeurIPS 2019 Jiezhang Cao, Langyuan Mo, Yifan Zhang, Kui Jia, Chunhua Shen, Mingkui Tan

Multiple marginal matching problem aims at learning mappings to match a source domain to multiple target domains and it has attracted great attention in many applications, such as multi-domain image translation.

Image Generation Translation

Geometry-aware Generation of Adversarial and Cooperative Point Clouds

no code implementations25 Sep 2019 Yuxin Wen, Jiehong Lin, Ke Chen, Kui Jia

Recent studies show that machine learning models are vulnerable to adversarial examples.


PARN: Position-Aware Relation Networks for Few-Shot Learning

1 code implementation ICCV 2019 Ziyang Wu, Yuwei Li, Lihua Guo, Kui Jia

However, due to the inherent local connectivity of CNN, the CNN-based relation network (RN) can be sensitive to the spatial position relationship of semantic objects in two compared images.

Few-Shot Learning Relational Reasoning +1

Orthogonal Deep Neural Networks

1 code implementation15 May 2019 Kui Jia, Shuai Li, Yuxin Wen, Tongliang Liu, DaCheng Tao

To this end, we first prove that DNNs are of local isometry on data distributions of practical interest; by using a new covering of the sample space and introducing the local isometry property of DNNs into generalization analysis, we establish a new generalization error bound that is both scale- and range-sensitive to singular value spectrum of each of networks' weight matrices.

Image Classification

Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers

no code implementations25 Apr 2019 Kui Jia, Jiehong Lin, Mingkui Tan, DaCheng Tao

Such a perspective enables us to study deep multi-view learning in the context of regularized network training, for which we present control experiments of benchmark image classification to show the efficacy of our proposed CorrReg.

3D Object Recognition General Classification +3

BIT: Biologically Inspired Tracker

1 code implementation23 Apr 2019 Bolun Cai, Xiangmin Xu, Xiaofen Xing, Kui Jia, Jie Miao, DaCheng Tao

Visual tracking is challenging due to image variations caused by various factors, such as object deformation, scale change, illumination change and occlusion.

Visual Tracking

Domain-Symmetric Networks for Adversarial Domain Adaptation

1 code implementation CVPR 2019 Yabin Zhang, Hui Tang, Kui Jia, Mingkui Tan

Since target samples are unlabeled, we also propose a scheme of cross-domain training to help learn the target classifier.

Unsupervised Domain Adaptation

Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection

2 code implementations5 Mar 2019 Zhixin Wang, Kui Jia

We also propose component variants of F-ConvNet, including an FCN variant that extracts multi-resolution frustum features, and a refined use of F-ConvNet over a reduced 3D space.

3D Object Detection object-detection +1

You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding

no code implementations12 Feb 2019 Chaorui Deng, Qi Wu, Guanghui Xu, Zhuliang Yu, Yanwu Xu, Kui Jia, Mingkui Tan

Most state-of-the-art methods in VG operate in a two-stage manner, wherein the first stage an object detector is adopted to generate a set of object proposals from the input image and the second stage is simply formulated as a cross-modal matching problem that finds the best match between the language query and all region proposals.

object-detection Object Detection +2

Coupled Recurrent Network (CRN)

no code implementations25 Dec 2018 Lin Sun, Kui Jia, Yuejia Shen, Silvio Savarese, Dit Yan Yeung, Bertram E. Shi

To learn from these heterogenous input sources, existing methods reply on two-stream architectural designs that contain independent, parallel streams of Recurrent Neural Networks (RNNs).

Action Recognition In Videos Multi-Person Pose Estimation +2

S-System, Geometry, Learning, and Optimization: A Theory of Neural Networks

no code implementations27 Sep 2018 Shuai Li, Kui Jia

We present a formal measure-theoretical theory of neural networks (NN) built on {\it probability coupling theory}.

Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision

no code implementations21 Sep 2018 Kun Zhou, Jinmiao Cai, Yao Li, Yulong Shi, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu

In this paper, a novel deep-learning based framework is proposed to infer 3D human poses from a single image.

3D Human Pose Estimation

Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data

2 code implementations ECCV 2018 Yabin Zhang, Hui Tang, Kui Jia

Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples.

Fine-Grained Visual Categorization Meta-Learning

FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information

no code implementations25 Jun 2018 Yulong Shi, Xiaoguang Han, Nianjuan Jiang, Kun Zhou, Kui Jia, Jiangbo Lu

Although significant advances have been made in the area of human poses estimation from images using deep Convolutional Neural Network (ConvNet), it remains a big challenge to perform 3D pose inference in-the-wild.

3D Human Pose Estimation

Part-Aware Fine-grained Object Categorization using Weakly Supervised Part Detection Network

2 code implementations16 Jun 2018 Yabin Zhang, Kui Jia, Zhixin Wang

In this work, we propose a Weakly Supervised Part Detection Network (PartNet) that is able to detect discriminative local parts for use of fine-grained categorization.

Object Categorization

Deep Sampling Networks

no code implementations4 Dec 2017 Bolun Cai, Xiangmin Xu, Kailing Guo, Kui Jia, DaCheng Tao

With the powerful down-sampling process, the co-training DSN set a new state-of-the-art performance for image super-resolution.

Image Compression Image Super-Resolution

A Joint Intrinsic-Extrinsic Prior Model for Retinex

no code implementations ICCV 2017 Bolun Cai, Xianming Xu, Kailing Guo, Kui Jia, Bin Hu, DaCheng Tao

We propose a joint intrinsic-extrinsic prior model to estimate both illumination and reflectance from an observed image.

Lattice Long Short-Term Memory for Human Action Recognition

no code implementations ICCV 2017 Lin Sun, Kui Jia, Kevin Chen, Dit Yan Yeung, Bertram E. Shi, Silvio Savarese

This method effectively enhances the ability to model dynamics across time and addresses the non-stationary issue of long-term motion dynamics without significantly increasing the model complexity.

Action Recognition Optical Flow Estimation +1

Automatic Discoveries of Physical and Semantic Concepts via Association Priors of Neuron Groups

no code implementations30 Dec 2016 Shuai Li, Kui Jia, Xiaogang Wang

The recent successful deep neural networks are largely trained in a supervised manner.

Improving training of deep neural networks via Singular Value Bounding

no code implementations CVPR 2017 Kui Jia

To this end, we propose to constrain the solutions of weight matrices in the orthogonal feasible set during the whole process of network training, and achieve this by a simple yet effective method called Singular Value Bounding (SVB).

General Classification Image Classification +2

Multi-task CNN Model for Attribute Prediction

no code implementations4 Jan 2016 Abrar H. Abdulnabi, Gang Wang, Jiwen Lu, Kui Jia

Each CNN will generate attribute-specific feature representations, and then we apply multi-task learning on the features to predict their attributes.

Multi-Task Learning

Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks

no code implementations ICCV 2015 Lin Sun, Kui Jia, Dit-yan Yeung, Bertram E. Shi

Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the involved humans and objects.

Action Recognition Image Classification +1

Robust Face Recognition by Constrained Part-based Alignment

no code implementations20 Jan 2015 Yuting Zhang, Kui Jia, Yueming Wang, Gang Pan, Tsung-Han Chan, Yi Ma

By assuming a human face as piece-wise planar surfaces, where each surface corresponds to a facial part, we develop in this paper a Constrained Part-based Alignment (CPA) algorithm for face recognition across pose and/or expression.

Face Alignment Face Recognition +1

DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition

no code implementations CVPR 2014 Lin Sun, Kui Jia, Tsung-Han Chan, Yuqiang Fang, Gang Wang, Shuicheng Yan

In this paper, we propose to combine SFA with deep learning techniques to learn hierarchical representations from the video data itself.

Action Recognition Temporal Action Localization

PCANet: A Simple Deep Learning Baseline for Image Classification?

2 code implementations14 Apr 2014 Tsung-Han Chan, Kui Jia, Shenghua Gao, Jiwen Lu, Zinan Zeng, Yi Ma

In this work, we propose a very simple deep learning network for image classification which comprises only the very basic data processing components: cascaded principal component analysis (PCA), binary hashing, and block-wise histograms.

Classification Face Recognition +5

Learning by Associating Ambiguously Labeled Images

no code implementations CVPR 2013 Zinan Zeng, Shijie Xiao, Kui Jia, Tsung-Han Chan, Shenghua Gao, Dong Xu, Yi Ma

Our framework is motivated by the observation that samples from the same class repetitively appear in the collection of ambiguously labeled training images, while they are just ambiguously labeled in each image.

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