Search

In many binary segmentation tasks, most CNNs-based methods use a U-shape encoder-decoder network as their basic structure. They ignore two key problems when the encoder exchanges information with the decoder: one is the lack of interference control mechanism between them, the other is without considering the disparity of the contributions from different encoder levels. In this work, we propose a simple yet general gated network (GateNet) to tackle them all at once. With the help of multi-level gate units, the valuable context information from the encoder can be selectively transmitted to the decoder. In addition, we design a gated dual branch structure to build the cooperation among the features of different levels and improve the discrimination ability of the network. Furthermore, we introduce a "Fold" operation to improve the atrous convolution and form a novel folded atrous convolution, which can be flexibly embedded in ASPP or DenseASPP to accurately localize foreground objects of various scales. GateNet can be easily generalized to many binary segmentation tasks, including general and specific object segmentation and multi-modal segmentation. Without bells and whistles, our network consistently performs favorably against the state-of-the-art methods under 10 metrics on 33 datasets of 10 binary segmentation tasks. [ABSTRACT FROM AUTHOR]

Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely applied. While general depth sensors produce the noisy and sparse depth information, which brings the depth-based networks with irreversible interference. In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD). Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. In this way, the depth information can be completed and purified. Moreover, we introduce a multi-modal filtered transformer (MFT) module, which equips with three modality-specific filters to generate the transformer-enhanced feature for each modality. The proposed model works in a depth-free style during the testing phase. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time. And, the resulted depth map can help existing RGB-D SOD methods obtain significant performance gain. [ABSTRACT FROM AUTHOR]

Static and moving objects often occur in real-life videos. Most video object segmentation methods only focus on extracting and exploiting motion cues to perceive moving objects. Once faced with the frames of static objects, the moving object predictors may predict failed results caused by uncertain motion information, such as low-quality optical flow maps. Besides, different sources such as RGB, depth, optical flow and static saliency can provide useful information about the objects. However, existing approaches only consider either the RGB or RGB and optical flow. In this paper, we propose a novel adaptive multi-source predictor for zero-shot video object segmentation (ZVOS). In the static object predictor, the RGB source is converted to depth and static saliency sources, simultaneously. In the moving object predictor, we propose the multi-source fusion structure. First, the spatial importance of each source is highlighted with the help of the interoceptive spatial attention module (ISAM). Second, the motion-enhanced module (MEM) is designed to generate pure foreground motion attention for improving the representation of static and moving features in the decoder. Furthermore, we design a feature purification module (FPM) to filter the inter-source incompatible features. By using the ISAM, MEM and FPM, the multi-source features are effectively fused. In addition, we put forward an adaptive predictor fusion network (APF) to evaluate the quality of the optical flow map and fuse the predictions from the static object predictor and the moving object predictor in order to prevent over-reliance on the failed results caused by low-quality optical flow maps. Experiments show that the proposed model outperforms the state-of-the-art methods on three challenging ZVOS benchmarks. And, the static object predictor precisely predicts a high-quality depth map and static saliency map at the same time. [ABSTRACT FROM AUTHOR]

Clinohumite is a potentially abundant silicate mineral with high water concentration (2~3 wt% H2O) that is generated from dehydration of serpentine-group minerals in subduction zones. Previous studies show that fluorine substitution (OH- = F-) can stabilize clinohumite to significantly higher temperature in subduction zones, although temperatures within the slabs are thought to be well within the stability field of both F-bearing and OH-clinohumite. We collected in-situ high-temperature Raman and Fourier transform infrared (FTIR) spectra for both the synthetic [Mg9Si4O16(OH)2] and natural [Mg7.84Fe0.58Mn0.01Ti0.25(SiO4)4O0.5(OH)1.30F0.20] clinohumite samples up to 1243 K. Three OH bands above 3450 cm–1 are detected for both the natural and synthetic samples with negative temperature dependence, due to neighboring H-H repulsion in the crystal structure. Additional OH peaks are detected for the natural sample below 3450 cm–1 with positive temperature dependence, which could be explained by non-polar F- substitution in the OH site. Hence, F- substitution significantly changes the high-temperature behavior of hydrogen bonds in the humite-group minerals. On the other hand, we evaluated the mode Grüneisen parameters (γiP, γiT), as well as the intrinsic anharmonic parameters (ai) for clinohumite, chondrodite, and phase A, the dense hydrous magnesium silicate (DHMS) phases along the brucite–forsterite join. The estimated averaged anharmonic parameters (ai_avg) for these DHMS phases are systematically smaller than those of olivine. To model the thermodynamic properties of minerals (such as heat capacity) at the high-temperature conditions of the mantle, the DeBye model, which simply approximates the lattice vibrations as harmonic oscillators, is commonly used. In contrast to forsterite, such quasi-harmonic approximations are valid for clinohumite at subduction zone temperatures, as the anharmonic contribution is no more than 2% when extrapolated to 2000 K. Hence, the classic DeBye model can reasonably simulate the thermodynamic properties of these DHMS phases in subduction zones. [ABSTRACT FROM AUTHOR]