Deep convolutional neural networks (CNNs) have delivered superior performance in many computer vision tasks. In this paper, we propose a novel deep fully convolutional network model for accurate ...salient object detection. The key contribution of this work is to learn deep uncertain convolutional features (UCF), which encourage the robustness and accuracy of saliency detection. We achieve this via introducing a reformulated dropout (R-dropout) after specific convolutional layers to construct an uncertain ensemble of internal feature units. In addition, we propose an effective hybrid upsampling method to reduce the checkerboard artifacts of deconvolution operators in our decoder network. The proposed methods can also be applied to other deep convolutional networks. Compared with existing saliency detection methods, the proposed UCF model is able to incorporate uncertainties for more accurate object boundary inference. Extensive experiments demonstrate that our proposed saliency model performs favorably against state-of-the-art approaches. The uncertain feature learning mechanism as well as the upsampling method can significantly improve performance on other pixel-wise vision tasks.
Deep Neural Networks (DNNs) have substantially improved the state-of-the-art in salient object detection. However, training DNNs requires costly pixel-level annotations. In this paper, we leverage ...the observation that image-level tags provide important cues of foreground salient objects, and develop a weakly supervised learning method for saliency detection using image-level tags only. The Foreground Inference Network (FIN) is introduced for this challenging task. In the first stage of our training method, FIN is jointly trained with a fully convolutional network (FCN) for image-level tag prediction. A global smooth pooling layer is proposed, enabling FCN to assign object category tags to corresponding object regions, while FIN is capable of capturing all potential foreground regions with the predicted saliency maps. In the second stage, FIN is fine-tuned with its predicted saliency maps as ground truth. For refinement of ground truth, an iterative Conditional Random Field is developed to enforce spatial label consistency and further boost performance. Our method alleviates annotation efforts and allows the usage of existing large scale training sets with image-level tags. Our model runs at 60 FPS, outperforms unsupervised ones with a large margin, and achieves comparable or even superior performance than fully supervised counterparts.
Traffic forecasting is a challenging problem in the transportation research field as the complexity and non-stationary changing of the traffic data, thus the key to the issue is how to explore proper ...spatial and temporal characteristics. Based on this thought, many creative methods have been proposed, in which Graph Convolution Network (GCN) based methods have shown promising performance. However, these methods depend on the graph construction, which mainly uses the prior knowledge of the road network. Recently, some works realized the fact of the road network graph changing and tried to construct dynamic graphs for GCN, but they do not fully exploit the spatial and temporal properties of the traffic data in the graph construction. In this paper, we propose a novel dynamic graph convolution network for traffic forecasting, in which a latent network is introduced to extract spatial-temporal features for constructing the dynamic road network graph matrices adaptively. The proposed method is evaluated on several traffic datasets and the experimental results show that it outperforms the state of the art traffic forecasting methods. The website of the code is https://github.com/guokan987/DGCN.git .
Low-light images typically suffer from two problems. First, they have low visibility (i.e., small pixel values). Second, noise becomes significant and disrupts the image content, due to low ...signal-to-noise ratio. Most existing lowlight image enhancement methods, however, learn from noise-negligible datasets. They rely on users having good photographic skills in taking images with low noise. Unfortunately, this is not the case for majority of the low-light images. While concurrently enhancing a low-light image and removing its noise is ill-posed, we observe that noise exhibits different levels of contrast in different frequency layers, and it is much easier to detect noise in the lowfrequency layer than in the high one. Inspired by this observation, we propose a frequency-based decompositionand- enhancement model for low-light image enhancement. Based on this model, we present a novel network that first learns to recover image objects in the low-frequency layer and then enhances high-frequency details based on the recovered image objects. In addition, we have prepared a new low-light image dataset with real noise to facilitate learning. Finally, we have conducted extensive experiments to show that the proposed method outperforms state-of-the-art approaches in enhancing practical noisy low-light images.
Tracking the sliding of grain boundaries at the atomic scale Wang, Lihua; Zhang, Yin; Zeng, Zhi ...
Science (American Association for the Advancement of Science),
2022-Mar-18, 2022-03-18, 20220318, Letnik:
375, Številka:
6586
Journal Article
Recenzirano
Grain boundaries (GBs) play an important role in the mechanical behavior of polycrystalline materials. Despite decades of investigation, the atomic-scale dynamic processes of GB deformation remain ...elusive, particularly for the GBs in polycrystals, which are commonly of the asymmetric and general type. We conducted an in situ atomic-resolution study to reveal how sliding-dominant deformation is accomplished at general tilt GBs in platinum bicrystals. We observed either direct atomic-scale sliding along the GB or sliding with atom transfer across the boundary plane. The latter sliding process was mediated by movements of disconnections that enabled the transport of GB atoms, leading to a previously unrecognized mode of coupled GB sliding and atomic plane transfer. These results enable an atomic-scale understanding of how general GBs slide in polycrystalline materials.
Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak ...supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels. As the subitizing information provides an instant judgement on the number of salient items, it is naturally related to detecting salient instances and may help separate instances of the same class while grouping different parts of the same instance. Inspired by this observation, we propose to use class and subitizing labels as weak supervision for the SID problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids. This complementary information is then fused to produce a salient instance map. To facilitate the learning process, we further propose a progressive training scheme to reduce label noise and the corresponding noise learned by the model, via reciprocating the model with progressive salient instance prediction and model refreshing. Our extensive evaluations show that the proposed method plays favorably against carefully designed baseline methods adapted from related tasks.
Recent researches revealed object detection networks using the simple "classification loss + localization loss" training objective are not effectively optimized in many cases, while providing ...additional constraints on network features could effectively improve object detection quality. Specifically, some works used constraints on training sample relations to successfully learn discriminative network features. Based on these observations, we propose Structural Constraint for improving object detection quality. Structural constraint supervises feature learning in classification and localization network branches with Fisher Loss and Equi-proportion Loss respectively, by requiring feature similarities of training sample pairs to be consistent with corresponding ground truth label similarities. Structural constraint could be applied to all object detection network architectures with the assist of our Proxy Feature design. Our experiment results showed that structural constraint mechanism is able to optimize object class instances' distribution in network feature space, and consequently detection results. Evaluations on MSCOCO2017 and KITTI datasets showed that our structural constraint mechanism is able to assist baseline networks to outperform modern counterpart detectors in terms of object detection quality.
This paper presents a new model, Semantics-enhanced Generative Adversarial Network (SEGAN), for fine-grained text-to-image generation. We introduce two modules, a Semantic Consistency Module (SCM) ...and an Attention Competition Module (ACM), to our SEGAN. The SCM incorporates image-level semantic consistency into the training of the Generative Adversarial Network (GAN), and can diversify the generated images and improve their structural coherence. A Siamese network and two types of semantic similarities are designed to map the synthesized image and the groundtruth image to nearby points in the latent semantic feature space. The ACM constructs adaptive attention weights to differentiate keywords from unimportant words, and improves the stability and accuracy of SEGAN. Extensive experiments demonstrate that our SEGAN significantly outperforms existing state-of-the-art methods in generating photo-realistic images. All source codes and models will be released for comparative study.
It is well recognized that expressions can significantly change facial geometry that results in a severe problem for robust 3D face recognition. So it is crucial for many applications that how to ...extract expression-robust features to describe 3D faces. In this paper, we develop a novel 3D face recognition algorithm using Local Binary Pattern (LBP) under expression varieties, which is an extension of the LBP operator widely used in ordinary facial analysis. First, to depict the human face more accurately and reduce the effect of facial local distortion for face recognition, a special feature-based 3D face division scheme is proposed. Then, the LBP representation framework for 3D faces is described, and the facial depth and normal information are extracted and encoded by LBP, to reduce the expression effect. For each face region, the statistical histogram is utilized to summarize the facial details, and accordingly three matching strategies are presented to address the recognition task. Finally, the proposed 3D face recognition algorithm is tested on BJUT-3D and FRGC v2.0 databases, achieves promising results, and concludes that it is feasible and valid to apply the LBP representation framework on 3D face recognition.
► We develop a 3D face recognition algorithm using LBP under expression varieties. ► We propose a special feature-based 3D face division scheme. ► We design a 3D face descriptor based on LBP to catch the tiny facial expressions. ► We design three matching strategies for LBP to address the recognition task.
Tensor clustering is an important tool that exploits intrinsically rich structures in real-world multiarray or Tensor datasets. Often in dealing with those datasets, standard practice is to use ...subspace clustering that is based on vectorizing multiarray data. However, vectorization of tensorial data does not exploit complete structure information. In this paper, we propose a subspace clustering algorithm without adopting any vectorization process. Our approach is based on a novel heterogeneous Tucker decomposition model taking into account cluster membership information. We propose a new clustering algorithm that alternates between different modes of the proposed heterogeneous tensor model. All but the last mode have closed-form updates. Updating the last mode reduces to optimizing over the multinomial manifold for which we investigate second order Riemannian geometry and propose a trust-region algorithm. Numerical experiments show that our proposed algorithm compete effectively with state-of-the-art clustering algorithms that are based on tensor factorization.
PDF
