skip to main content

Search for: All records

Creators/Authors contains: "Tian, Y"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Free, publicly-accessible full text available January 1, 2023
  2. Free, publicly-accessible full text available January 1, 2023
  3. The success of supervised learning requires large-scale ground truth labels which are very expensive, time- consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are developed. Unlike most existing self-supervised methods to learn only 2D image features or only 3D point cloud features, this paper presents a novel and effective self-supervised learning approach to jointly learn both 2D image features and 3D point cloud features by exploiting cross-modality and cross-view correspondences without using any human annotated labels. Specifically, 2D image features of rendered images from different views are extracted by a 2D convolutional neural network, and 3D point cloud features are extracted by a graph convolution neural network. Two types of features are fed into a two-layer fully connected neural network to estimate the cross-modality correspondence. The three networks are jointly trained (i.e. cross-modality) by verifying whether two sampled data of different modalities belong to the same object, meanwhile, the 2D convolutional neural network is additionally optimized through minimizing intra-object distance while maximizing inter-object distance of rendered images in different views (i.e. cross-view). The effectiveness of the learned 2D and 3D features is evaluated by transferring them on five different tasks includingmore »multi-view 2D shape recognition, 3D shape recognition, multi-view 2D shape retrieval, 3D shape retrieval, and 3D part-segmentation. Extensive evaluations on all the five different tasks across different datasets demonstrate strong generalization and effectiveness of the learned 2D and 3D features by the proposed self-supervised method.« less
  4. Cross-modal retrieval aims to learn discriminative and modal-invariant features for data from different modalities. Unlike the existing methods which usually learn from the features extracted by offline networks, in this paper, we pro- pose an approach to jointly train the components of cross- modal retrieval framework with metadata, and enable the network to find optimal features. The proposed end-to-end framework is updated with three loss functions: 1) a novel cross-modal center loss to eliminate cross-modal discrepancy, 2) cross-entropy loss to maximize inter-class variations, and 3) mean-square-error loss to reduce modality variations. In particular, our proposed cross-modal center loss minimizes the distances of features from objects belonging to the same class across all modalities. Extensive experiments have been conducted on the retrieval tasks across multi-modalities including 2D image, 3D point cloud and mesh data. The proposed framework significantly outperforms the state-of-the-art methods for both cross-modal and in-domain retrieval for 3D objects on the ModelNet10 and ModelNet40 datasets.
  5. Recently 3D scene understanding attracts attention for many applications, however, annotating a vast amount of 3D data for training is usually expensive and time consuming. To alleviate the needs of ground truth, we propose a self-supervised schema to learn 4D spatio-temporal features (i.e. 3 spatial dimensions plus 1 temporal dimension) from dynamic point cloud data by predicting the temporal order of sampled and shuffled point cloud clips. 3D sequential point cloud contains precious geometric and depth information to better recognize activities in 3D space compared to videos. To learn the 4D spatio-temporal features, we introduce 4D convolution neural networks to predict the temporal order on a self-created large scale dataset, NTU- PCLs, derived from the NTU-RGB+D dataset. The efficacy of the learned 4D spatio-temporal features is verified on two tasks: 1) Self-supervised 3D nearest neighbor retrieval; and 2) Self-supervised representation learning transferred for action recognition on smaller 3D dataset. Our extensive experiments prove the effectiveness of the proposed self-supervised learning method which achieves comparable results w.r.t. the fully-supervised methods on action recognition on MSRAction3D dataset.
  6. Scene flow depicts the dynamics of a 3D scene, which is critical for various applications such as autonomous driving, robot navigation, AR/VR, etc. Conventionally, scene ?ow is estimated from dense/regular RGB video frames. With the development of depth-sensing technologies, precise 3D measurements are available via point clouds which have sparked new research in 3D scene flow. Nevertheless, it remains challenging to extract scene flow from point clouds due to the sparsity and irregularity in typical point cloud sampling patterns. One major issue related to irregular sampling is identified as the randomness during point set abstraction/feature extraction an elementary process in many flow estimation scenarios. A novel Spatial Abstraction with Attention (SA2) layer is accordingly proposed to alleviate the unstable abstraction problem. Moreover, a Temporal Abstraction with Attention (TA2) layer is proposed to rectify attention in temporal domain, leading to benefits with motions scaled in a larger range. Extensive analysis and experiments verified the motivation and significant performance gains of our method, dubbed as Flow Estimation via Spatial-Temporal Attention (FESTA), when compared to several state-of-the-art benchmarks of scene flow estimation.
  7. While contrastive approaches of self-supervised learning (SSL) learn representations by minimizing the distance between two augmented views of the same data point (positive pairs) and maximizing views from different data points (negative pairs), recent \emph{non-contrastive} SSL (e.g., BYOL and SimSiam) show remarkable performance {\it without} negative pairs, with an extra learnable predictor and a stop-gradient operation. A fundamental question rises: why they do not collapse into trivial representation? In this paper, we answer this question via a simple theoretical study and propose a novel approach, \ourmethod{}, that \emph{directly} sets the linear predictor based on the statistics of its inputs, rather than trained with gradient update. On ImageNet, it performs comparably with more complex two-layer non-linear predictors that employ BatchNorm and outperforms linear predictor by 2.5 in 300-epoch training (and 5 in 60-epoch). \ourmethod{} is motivated by our theoretical study of the nonlinear learning dynamics of non-contrastive SSL in simple linear networks. Our study yields conceptual insights into how non-contrastive SSL methods learn, how they avoid representational collapse, and how multiple factors, like predictor networks, stop-gradients, exponential moving averages, and weight decay all come into play. Our simple theory recapitulates the results of real-world ablation studies in both STL-10 and ImageNet.more »Code is released.« less
  8. 3D point cloud completion has been a long-standing challenge at scale, and corresponding per-point supervised training strategies suffered from cumbersome annotations. 2D supervision has recently emerged as a promising alternative for 3D tasks, but specific approaches for 3D point cloud completion still remain to be explored. To overcome these limitations, we propose an end-to-end method that directly lifts a single depth map to a completed point cloud. With one depth map as input, a multi-way novel depth view synthesis network (NDVNet) is designed to infer coarsely completed depth maps under various viewpoints. Meanwhile, a geometric depth perspective rendering module is introduced to utilize the raw input depth map to generate a reprojected depth map for each view. Therefore, the two parallelly generated depth maps for each view are further concatenated and refined by a depth completion network (DCNet). The final completed point cloud is fused from all refined depth views. Experimental results demonstrate the effectiveness of our proposed approach composed of aforementioned components, to produce high-quality, state-of-the-art results on the popular SUNCG benchmark.