This paper aims at high-accuracy 3D object detection in autonomous driving scenario. We propose Multi-View 3D networks (MV3D), a sensory-fusion framework that takes both LIDAR point cloud and RGB images as input and predicts oriented 3D bounding boxes. We encode the sparse 3D point cloud with a compact multi-view representation. The network is composed of two subnetworks: one for 3D object proposal generation and another for multi-view feature fusion. The proposal network generates 3D candidate boxes efficiently from the bird's eye view representation of 3D point cloud. We design a deep fusion scheme to combine region-wise features from multiple views and enable interactions between intermediate layers of different paths. Experiments on the challenging KITTI benchmark show that our approach outperforms the state-of-the-art by around 25% and 30% AP on the tasks of 3D localization and 3D detection. In addition, for 2D detection, our approach obtains 10.3% higher AP than the state-of-the-art on the hard data among the LIDAR-based methods.

Abstract-Convolutional network techniques have recently achieved great success in vision based detection tasks. This paper introduces the recent development of our research on transplanting the fully convolutional network technique to the detection tasks on 3D range scan data. Specifically, the scenario is set as the vehicle detection task from the range data of Velodyne 64E lidar. We proposes to present the data in a 2D point map and use a single 2D end-to-end fully convolutional network to predict the objectness confidence and the bounding boxes simultaneously. By carefully design the bounding box encoding, it is able to predict full 3D bounding boxes even using a 2D convolutional network. Experiments on the KITTI dataset shows the state-ofthe-art performance of the proposed method.

No abstract

Image saliency detection is an active research topic in the community of computer vision and multimedia. Fusing complementary RGB and thermal infrared data has been proven to be effective for image saliency detection. In this paper, we propose an effective approach for RGB-T image saliency detection. Our approach relies on a novel collaborative graph learning algorithm. In particular, we take superpixels as graph nodes, and collaboratively use hierarchical deep features to jointly learn graph affinity and node saliency in a unified optimization framework. Moreover, we contribute a more challenging dataset for the purpose of RGB-T image saliency detection, which contains 1000 spatially aligned RGB-T image pairs and their ground truth annotations. Extensive experiments on the public dataset and the newly created dataset suggest that the proposed approach performs favorably against the state-of-the-art RGB-T saliency detection methods.

Pseudo-healthy synthesis is the task of creating a subject-specific 'healthy' image from a pathological one. Such images can be helpful in tasks such as anomaly detection and understanding changes induced by pathology and disease. In this paper, we present a model that is encouraged to disentangle the information of pathology from what seems to be healthy. We disentangle what appears to be healthy and where disease is as a segmentation map, which are then recombined by a network to reconstruct the input disease image. We train our models adversarially using either paired or unpaired settings, where we pair disease images and maps when available. We quantitatively and subjectively, with a human study, evaluate the quality of pseudo-healthy images using several criteria. We show in a series of experiments, performed on ISLES, BraTS and Cam-CAN datasets, that our method is better than several baselines and methods from the literature. We also show that due to better training processes we could recover deformations, on surrounding tissue, caused by disease. Our implementation is publicly available at https://github.com/xiat0616/pseudo-healthy-synthesis.

No abstract

The aim of this study was to evaluate the effect of a porous tantalum rod implant for the treatment of early femoral head necrosis. From April 2007 to June 2009, a total of 35 femoral head necrosis patients (with 49 hips) were treated with core decompression in combination with the insertion of a porous tantalum rod. The mean age was 38.2 years (22-50 years) and the mean follow-up period was 15.2 months (12-36 months). The surgical time and blood loss were recorded. The Harris hip scores and radiological results were adopted for evaluation. The mean surgical time was 35 min, and the mean blood loss was 50 ml. The mean Harris score improved from 48.3 ± 3.2 preoperative to 83.7 ± 4.1 at the last follow-up (p < 0.05). Eight affected hips exhibited progressive pain including three hips that progressed to femoral collapse, and one revision followed by total hip arthroplasty (THA). For the patient who underwent revision and THA, the articular cartilage surface was seen to be damaged and fragmented. High-density metal particle residuals were observed on radiograph in the bone channel and femoral marrow cavity. We conclude that the selection criteria for porous tantalum implants should be early and intermediate stages of femoral head necrosis. Further study is warranted to reveal whether the metal particles released play a role in the progression of pain and failure.

Large-scale supervised datasets are crucial to train con volutional neural networks (CNNs)for various computer vi sion problems. However, obtaining a massive amount of well-labeled data is usually very expensive and time con suming. In this paper, we introduce a general framework to train CNNs with only a limited number of clean labels and millions of easily obtained noisy labels. We model the relationships between images, class labels and label noises with a probabilistic graphical model and further integrate it into an end-to-end deep learning system. To demonstrate the effectiveness of our approach, we collect a large-scale real-world clothing classification dataset with both noisy and clean labels. Experiments on this dataset indicate that our approach can better correct the noisy labels and im proves the performance of trained CNNs.