arXiv subjects

Jianfei Cai

Publications and source records attributed to Jianfei Cai.

At least 181 records · Page 10Linked to original sources

arXiv2019

Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention

Lesion detection from computed tomography (CT) scans is challenging compared to natural object detection because of two major reasons: small lesion size and small inter-class variation. Firstly, the lesions usually only occupy a small region in the CT image. The feature of such small region may not be able to provide sufficient information due to its limited spatial feature resolution. Secondly, in CT scans, the lesions are often indistinguishable from the background since the lesion and non-lesion areas may have very similar appearances. To tackle both problems, we need to enrich the feature representation and improve the feature discriminativeness. Therefore, we introduce a dual-attention mechanism to the 3D contextual lesion detection framework, including the cross-slice contextual attention to selectively aggregate the information from different slices through a soft re-sampling process. Moreover, we propose intra-slice spatial attention to focus the feature learning in the most prominent regions. Our method can be easily trained end-to-end without adding heavy overhead on the base detection network. We use DeepLesion dataset and train a universal lesion detector to detect all kinds of lesions such as liver tumors, lung nodules, and so on. The results show that our model can significantly boost the results of the baseline lesion detector (with 3D contextual information) but using much fewer slices.

cs.CV↗

arXiv2019

Region Deformer Networks for Unsupervised Depth Estimation from Unconstrained Monocular Videos

While learning based depth estimation from images/videos has achieved substantial progress, there still exist intrinsic limitations. Supervised methods are limited by a small amount of ground truth or labeled data and unsupervised methods for monocular videos are mostly based on the static scene assumption, not performing well on real world scenarios with the presence of dynamic objects. In this paper, we propose a new learning based method consisting of DepthNet, PoseNet and Region Deformer Networks (RDN) to estimate depth from unconstrained monocular videos without ground truth supervision. The core contribution lies in RDN for proper handling of rigid and non-rigid motions of various objects such as rigidly moving cars and deformable humans. In particular, a deformation based motion representation is proposed to model individual object motion on 2D images. This representation enables our method to be applicable to diverse unconstrained monocular videos. Our method can not only achieve the state-of-the-art results on standard benchmarks KITTI and Cityscapes, but also show promising results on a crowded pedestrian tracking dataset, which demonstrates the effectiveness of the deformation based motion representation. Code and trained models are available at https://github.com/haofeixu/rdn4depth.

cs.CV↗

arXiv2019

Visibility Constrained Generative Model for Depth-based 3D Facial Pose Tracking

In this paper, we propose a generative framework that unifies depth-based 3D facial pose tracking and face model adaptation on-the-fly, in the unconstrained scenarios with heavy occlusions and arbitrary facial expression variations. Specifically, we introduce a statistical 3D morphable model that flexibly describes the distribution of points on the surface of the face model, with an efficient switchable online adaptation that gradually captures the identity of the tracked subject and rapidly constructs a suitable face model when the subject changes. Moreover, unlike prior art that employed ICP-based facial pose estimation, to improve robustness to occlusions, we propose a ray visibility constraint that regularizes the pose based on the face model's visibility with respect to the input point cloud. Ablation studies and experimental results on Biwi and ICT-3DHP datasets demonstrate that the proposed framework is effective and outperforms completing state-of-the-art depth-based methods.

cs.CV↗

arXiv2019

3D Hand Shape and Pose Estimation from a Single RGB Image

This work addresses a novel and challenging problem of estimating the full 3D hand shape and pose from a single RGB image. Most current methods in 3D hand analysis from monocular RGB images only focus on estimating the 3D locations of hand keypoints, which cannot fully express the 3D shape of hand. In contrast, we propose a Graph Convolutional Neural Network (Graph CNN) based method to reconstruct a full 3D mesh of hand surface that contains richer information of both 3D hand shape and pose. To train networks with full supervision, we create a large-scale synthetic dataset containing both ground truth 3D meshes and 3D poses. When fine-tuning the networks on real-world datasets without 3D ground truth, we propose a weakly-supervised approach by leveraging the depth map as a weak supervision in training. Through extensive evaluations on our proposed new datasets and two public datasets, we show that our proposed method can produce accurate and reasonable 3D hand mesh, and can achieve superior 3D hand pose estimation accuracy when compared with state-of-the-art methods.

cs.CV↗

arXiv2019

Learning to Collocate Neural Modules for Image Captioning

We do not speak word by word from scratch; our brain quickly structures a pattern like \textsc{sth do sth at someplace} and then fill in the detailed descriptions. To render existing encoder-decoder image captioners such human-like reasoning, we propose a novel framework: learning to Collocate Neural Modules (CNM), to generate the `inner pattern' connecting visual encoder and language decoder. Unlike the widely-used neural module networks in visual Q\&A, where the language (ie, question) is fully observable, CNM for captioning is more challenging as the language is being generated and thus is partially observable. To this end, we make the following technical contributions for CNM training: 1) compact module design --- one for function words and three for visual content words (eg, noun, adjective, and verb), 2) soft module fusion and multi-step module execution, robustifying the visual reasoning in partial observation, 3) a linguistic loss for module controller being faithful to part-of-speech collocations (eg, adjective is before noun). Extensive experiments on the challenging MS-COCO image captioning benchmark validate the effectiveness of our CNM image captioner. In particular, CNM achieves a new state-of-the-art 127.9 CIDEr-D on Karpathy split and a single-model 126.0 c40 on the official server. CNM is also robust to few training samples, eg, by training only one sentence per image, CNM can halve the performance loss compared to a strong baseline.

cs.CV↗

arXiv2019

When Gaussian Process Meets Big Data: A Review of Scalable GPs

The vast quantity of information brought by big data as well as the evolving computer hardware encourages success stories in the machine learning community. In the meanwhile, it poses challenges for the Gaussian process (GP) regression, a well-known non-parametric and interpretable Bayesian model, which suffers from cubic complexity to data size. To improve the scalability while retaining desirable prediction quality, a variety of scalable GPs have been presented. But they have not yet been comprehensively reviewed and analyzed in order to be well understood by both academia and industry. The review of scalable GPs in the GP community is timely and important due to the explosion of data size. To this end, this paper is devoted to the review on state-of-the-art scalable GPs involving two main categories: global approximations which distillate the entire data and local approximations which divide the data for subspace learning. Particularly, for global approximations, we mainly focus on sparse approximations comprising prior approximations which modify the prior but perform exact inference, posterior approximations which retain exact prior but perform approximate inference, and structured sparse approximations which exploit specific structures in kernel matrix; for local approximations, we highlight the mixture/product of experts that conducts model averaging from multiple local experts to boost predictions. To present a complete review, recent advances for improving the scalability and capability of scalable GPs are reviewed. Finally, the extensions and open issues regarding the implementation of scalable GPs in various scenarios are reviewed and discussed to inspire novel ideas for future research avenues.

stat.ML↗

arXiv2019

Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task

With the wide development of black-box machine learning algorithms, particularly deep neural network (DNN), the practical demand for the reliability assessment is rapidly rising. On the basis of the concept that `Bayesian deep learning knows what it does not know,' the uncertainty of DNN outputs has been investigated as a reliability measure for the classification and regression tasks. However, in the image-caption retrieval task, well-known samples are not always easy-to-retrieve samples. This study investigates two aspects of image-caption embedding-and-retrieval systems. On one hand, we quantify feature uncertainty by considering image-caption embedding as a regression task, and use it for model averaging, which can improve the retrieval performance. On the other hand, we further quantify posterior uncertainty by considering the retrieval as a classification task, and use it as a reliability measure, which can greatly improve the retrieval performance by rejecting uncertain queries. The consistent performance of two uncertainty measures is observed with different datasets (MS COCO and Flickr30k), different deep learning architectures (dropout and batch normalization), and different similarity functions.

cs.CV↗

arXiv2019

Pluralistic Image Completion

Most image completion methods produce only one result for each masked input, although there may be many reasonable possibilities. In this paper, we present an approach for \textbf{pluralistic image completion} -- the task of generating multiple and diverse plausible solutions for image completion. A major challenge faced by learning-based approaches is that usually only one ground truth training instance per label. As such, sampling from conditional VAEs still leads to minimal diversity. To overcome this, we propose a novel and probabilistically principled framework with two parallel paths. One is a reconstructive path that utilizes the only one given ground truth to get prior distribution of missing parts and rebuild the original image from this distribution. The other is a generative path for which the conditional prior is coupled to the distribution obtained in the reconstructive path. Both are supported by GANs. We also introduce a new short+long term attention layer that exploits distant relations among decoder and encoder features, improving appearance consistency. When tested on datasets with buildings (Paris), faces (CelebA-HQ), and natural images (ImageNet), our method not only generated higher-quality completion results, but also with multiple and diverse plausible outputs.

cs.CV↗

arXiv2019

Scene Graph Generation with External Knowledge and Image Reconstruction

Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc. However, existing datasets are biased in terms of object and relationship labels, or often come with noisy and missing annotations, which makes the development of a reliable scene graph prediction model very challenging. In this paper, we propose a novel scene graph generation algorithm with external knowledge and image reconstruction loss to overcome these dataset issues. In particular, we extract commonsense knowledge from the external knowledge base to refine object and phrase features for improving generalizability in scene graph generation. To address the bias of noisy object annotations, we introduce an auxiliary image reconstruction path to regularize the scene graph generation network. Extensive experiments show that our framework can generate better scene graphs, achieving the state-of-the-art performance on two benchmark datasets: Visual Relationship Detection and Visual Genome datasets.

cs.CV↗

arXiv2019

Progress Regression RNN for Online Spatial-Temporal Action Localization in Unconstrained Videos

Previous spatial-temporal action localization methods commonly follow the pipeline of object detection to estimate bounding boxes and labels of actions. However, the temporal relation of an action has not been fully explored. In this paper, we propose an end-to-end Progress Regression Recurrent Neural Network (PR-RNN) for online spatial-temporal action localization, which learns to infer the action by temporal progress regression. Two new action attributes, called progression and progress rate, are introduced to describe the temporal engagement and relative temporal position of an action. In our method, frame-level features are first extracted by a Fully Convolutional Network (FCN). Subsequently, detection results and action progress attributes are regressed by the Convolutional Gated Recurrent Unit (ConvGRU) based on all the observed frames instead of a single frame or a short clip. Finally, a novel online linking method is designed to connect single-frame results to spatial-temporal tubes with the help of the estimated action progress attributes. Extensive experiments demonstrate that the progress attributes improve the localization accuracy by providing more precise temporal position of an action in unconstrained videos. Our proposed PR-RNN achieves the stateof-the-art performance for most of the IoU thresholds on two benchmark datasets.

cs.CV↗

arXiv2019

Real-time 3D Face-Eye Performance Capture of a Person Wearing VR Headset

Teleconference or telepresence based on virtual reality (VR) headmount display (HMD) device is a very interesting and promising application since HMD can provide immersive feelings for users. However, in order to facilitate face-to-face communications for HMD users, real-time 3D facial performance capture of a person wearing HMD is needed, which is a very challenging task due to the large occlusion caused by HMD. The existing limited solutions are very complex either in setting or in approach as well as lacking the performance capture of 3D eye gaze movement. In this paper, we propose a convolutional neural network (CNN) based solution for real-time 3D face-eye performance capture of HMD users without complex modification to devices. To address the issue of lacking training data, we generate massive pairs of HMD face-label dataset by data synthesis as well as collecting VR-IR eye dataset from multiple subjects. Then, we train a dense-fitting network for facial region and an eye gaze network to regress 3D eye model parameters. Extensive experimental results demonstrate that our system can efficiently and effectively produce in real time a vivid personalized 3D avatar with the correct identity, pose, expression and eye motion corresponding to the HMD user.

cs.CV↗

arXiv2018

Auto-Encoding Scene Graphs for Image Captioning

We propose Scene Graph Auto-Encoder (SGAE) that incorporates the language inductive bias into the encoder-decoder image captioning framework for more human-like captions. Intuitively, we humans use the inductive bias to compose collocations and contextual inference in discourse. For example, when we see the relation `person on bike', it is natural to replace `on' with `ride' and infer `person riding bike on a road' even the `road' is not evident. Therefore, exploiting such bias as a language prior is expected to help the conventional encoder-decoder models less likely overfit to the dataset bias and focus on reasoning. Specifically, we use the scene graph --- a directed graph ($\mathcal{G}$) where an object node is connected by adjective nodes and relationship nodes --- to represent the complex structural layout of both image ($\mathcal{I}$) and sentence ($\mathcal{S}$). In the textual domain, we use SGAE to learn a dictionary ($\mathcal{D}$) that helps to reconstruct sentences in the $\mathcal{S}\rightarrow \mathcal{G} \rightarrow \mathcal{D} \rightarrow \mathcal{S}$ pipeline, where $\mathcal{D}$ encodes the desired language prior; in the vision-language domain, we use the shared $\mathcal{D}$ to guide the encoder-decoder in the $\mathcal{I}\rightarrow \mathcal{G}\rightarrow \mathcal{D} \rightarrow \mathcal{S}$ pipeline. Thanks to the scene graph representation and shared dictionary, the inductive bias is transferred across domains in principle. We validate the effectiveness of SGAE on the challenging MS-COCO image captioning benchmark, e.g., our SGAE-based single-model achieves a new state-of-the-art $127.8$ CIDEr-D on the Karpathy split, and a competitive $125.5$ CIDEr-D (c40) on the official server even compared to other ensemble models.

cs.CV↗

arXiv2018

Understanding and Comparing Scalable Gaussian Process Regression for Big Data

As a non-parametric Bayesian model which produces informative predictive distribution, Gaussian process (GP) has been widely used in various fields, like regression, classification and optimization. The cubic complexity of standard GP however leads to poor scalability, which poses challenges in the era of big data. Hence, various scalable GPs have been developed in the literature in order to improve the scalability while retaining desirable prediction accuracy. This paper devotes to investigating the methodological characteristics and performance of representative global and local scalable GPs including sparse approximations and local aggregations from four main perspectives: scalability, capability, controllability and robustness. The numerical experiments on two toy examples and five real-world datasets with up to 250K points offer the following findings. In terms of scalability, most of the scalable GPs own a time complexity that is linear to the training size. In terms of capability, the sparse approximations capture the long-term spatial correlations, the local aggregations capture the local patterns but suffer from over-fitting in some scenarios. In terms of controllability, we could improve the performance of sparse approximations by simply increasing the inducing size. But this is not the case for local aggregations. In terms of robustness, local aggregations are robust to various initializations of hyperparameters due to the local attention mechanism. Finally, we highlight that the proper hybrid of global and local scalable GPs may be a promising way to improve both the model capability and scalability for big data.

stat.ML↗

arXiv2018

Keypoint Based Weakly Supervised Human Parsing

Fully convolutional networks (FCN) have achieved great success in human parsing in recent years. In conventional human parsing tasks, pixel-level labeling is required for guiding the training, which usually involves enormous human labeling efforts. To ease the labeling efforts, we propose a novel weakly supervised human parsing method which only requires simple object keypoint annotations for learning. We develop an iterative learning method to generate pseudo part segmentation masks from keypoint labels. With these pseudo masks, we train an FCN network to output pixel-level human parsing predictions. Furthermore, we develop a correlation network to perform joint prediction of part and object segmentation masks and improve the segmentation performance. The experiment results show that our weakly supervised method is able to achieve very competitive human parsing results. Despite our method only uses simple keypoint annotations for learning, we are able to achieve comparable performance with fully supervised methods which use the expensive pixel-level annotations.

cs.CV↗

arXiv2018

VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions

Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance compared with the answer itself, since it makes the question and answering process more understandable and traceable. To this end, we propose a new task of VQA-E (VQA with Explanation), where the computational models are required to generate an explanation with the predicted answer. We first construct a new dataset, and then frame the VQA-E problem in a multi-task learning architecture. Our VQA-E dataset is automatically derived from the VQA v2 dataset by intelligently exploiting the available captions. We have conducted a user study to validate the quality of explanations synthesized by our method. We quantitatively show that the additional supervision from explanations can not only produce insightful textual sentences to justify the answers, but also improve the performance of answer prediction. Our model outperforms the state-of-the-art methods by a clear margin on the VQA v2 dataset.

cs.CV↗

arXiv2018

T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks

Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images, that comprises an image translation network for enhancing realism of input images, followed by a depth prediction network. A key idea is having the first network act as a wide-spectrum input translator, taking in either synthetic or real images, and ideally producing minimally modified realistic images. This is done via a reconstruction loss when the training input is real, and GAN loss when synthetic, removing the need for heuristic self-regularization. The second network is trained on a task loss for synthetic image-depth pairs, with extra GAN loss to unify real and synthetic feature distributions. Importantly, the framework can be trained end-to-end, leading to good results, even surpassing early deep-learning methods that use real paired data.

cs.CV↗

arXiv2018

Zero-Annotation Object Detection with Web Knowledge Transfer

Object detection is one of the major problems in computer vision, and has been extensively studied. Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least image-level annotations. On the contrary, we propose an object detection method that does not require any form of human annotation on target tasks, by exploiting freely available web images. In order to facilitate effective knowledge transfer from web images, we introduce a multi-instance multi-label domain adaption learning framework with two key innovations. First of all, we propose an instance-level adversarial domain adaptation network with attention on foreground objects to transfer the object appearances from web domain to target domain. Second, to preserve the class-specific semantic structure of transferred object features, we propose a simultaneous transfer mechanism to transfer the supervision across domains through pseudo strong label generation. With our end-to-end framework that simultaneously learns a weakly supervised detector and transfers knowledge across domains, we achieved significant improvements over baseline methods on the benchmark datasets.

cs.CV↗

arXiv2018

Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features

Due to the fact that it is prohibitively expensive to completely annotate visual relationships, i.e., the (obj1, rel, obj2) triplets, relationship models are inevitably biased to object classes of limited pairwise patterns, leading to poor generalization to rare or unseen object combinations. Therefore, we are interested in learning object-agnostic visual features for more generalizable relationship models. By "agnostic", we mean that the feature is less likely biased to the classes of paired objects. To alleviate the bias, we propose a novel \texttt{Shuffle-Then-Assemble} pre-training strategy. First, we discard all the triplet relationship annotations in an image, leaving two unpaired object domains without obj1-obj2 alignment. Then, our feature learning is to recover possible obj1-obj2 pairs. In particular, we design a cycle of residual transformations between the two domains, to capture shared but not object-specific visual patterns. Extensive experiments on two visual relationship benchmarks show that by using our pre-trained features, naive relationship models can be consistently improved and even outperform other state-of-the-art relationship models. Code has been made available at: \url{https://github.com/yangxuntu/vrd}.

cs.CV↗