Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection

UAV's Status Is Worth Considering: A Fusion Representations Matching Method for Geo-Localization

Visual geo-localization plays a crucial role in positioning and navigation for unmanned aerial vehicles, whose goal is to match the same geographic target from different views. This is a challenging task due to the drastic variations in different viewpoints and appearances. Previous methods have been focused on mining features inside the images. However, they underestimated the influence of external elements and the interaction of various representations. Inspired by multimodal and bilinear pooling, we proposed a pioneering feature fusion network (MBF) to address these inherent differences between drone and satellite views. We observe that UAV's status, such as flight height, leads to changes in the size of image field of view. In addition, local parts of the target scene act a role of importance in extracting discriminative features. Therefore, we present two approaches to exploit those priors. The first module is to add status information to network by transforming them into word embeddings. Note that they concatenate with image embeddings in Transformer block to learn status-aware features. Then, global and local part feature maps from the same viewpoint are correlated and reinforced by hierarchical bilinear pooling (HBP) to improve the robustness of feature representation. By the above approaches, we achieve more discriminative deep representations facilitating the geo-localization more effectively. Our experiments on existing benchmark datasets show significant performance boosting, reaching the new state-of-the-art result. Remarkably, the recall@1 accuracy achieves 89.05% in drone localization task and 93.15% in drone navigation task in University-1652, and shows strong robustness at different flight heights in the SUES-200 dataset.

HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness

RGB-D saliency detection aims to fuse multi-modal cues to accurately localize salient regions. Existing works often adopt attention modules for feature modeling, with few methods explicitly leveraging fine-grained details to merge with semantic cues. Thus, despite the auxiliary depth information, it is still challenging for existing models to distinguish objects with similar appearances but at distinct camera distances. In this paper, from a new perspective, we propose a novel Hierarchical Depth Awareness network (HiDAnet) for RGB-D saliency detection. Our motivation comes from the observation that the multi-granularity properties of geometric priors correlate well with the neural network hierarchies. To realize multi-modal and multi-level fusion, we first use a granularity-based attention scheme to strengthen the discriminatory power of RGB and depth features separately. Then we introduce a unified cross dual-attention module for multi-modal and multi-level fusion in a coarse-to-fine manner. The encoded multi-modal features are gradually aggregated into a shared decoder. Further, we exploit a multi-scale loss to take full advantage of the hierarchical information. Extensive experiments on challenging benchmark datasets demonstrate that our HiDAnet performs favorably over the state-of-the-art methods by large margins. The source code can be found in https://github.com/Zongwei97/HIDANet/.

Improving RGB-D Salient Object Detection via Modality-Aware Decoder

Most existing RGB-D salient object detection (SOD) methods are primarily focusing on cross-modal and cross-level saliency fusion, which has been proved to be efficient and effective. However, these methods still have a critical limitation, i.e., their fusion patterns - typically the combination of selective characteristics and its variations, are too highly dependent on the network's non-linear adaptability. In such methods, the balances between RGB and D (Depth) are formulated individually considering the intermediate feature slices, but the relation at the modality level may not be learned properly. The optimal RGB-D combinations differ depending on the RGB-D scenarios, and the exact complementary status is frequently determined by multiple modality-level factors, such as D quality, the complexity of the RGB scene, and degree of harmony between them. Therefore, given the existing approaches, it may be difficult for them to achieve further performance breakthroughs, as their methodologies belong to some methods that are somewhat less modality sensitive. To conquer this problem, this paper presents the Modality-aware Decoder (MaD). The critical technical innovations include a series of feature embedding, modality reasoning, and feature back-projecting and collecting strategies, all of which upgrade the widely-used multi-scale and multi-level decoding process to be modality-aware. Our MaD achieves competitive performance over other state-of-the-art (SOTA) models without using any fancy tricks in the decoder's design. Codes and results will be publicly available at https://github.com/MengkeSong/MaD.

AMFuse: Add–Multiply-Based Cross-Modal Fusion Network for Multi-Spectral Semantic Segmentation

Multi-spectral semantic segmentation has shown great advantages under poor illumination conditions, especially for remote scene understanding of autonomous vehicles, since the thermal image can provide complementary information for RGB image. However, methods to fuse the information from RGB image and thermal image are still under-explored. In this paper, we propose a simple but effective module, add–multiply fusion (AMFuse) for RGB and thermal information fusion, consisting of two simple math operations—addition and multiplication. The addition operation focuses on extracting cross-modal complementary features, while the multiplication operation concentrates on the cross-modal common features. Moreover, the attention module and atrous spatial pyramid pooling (ASPP) modules are also incorporated into our proposed AMFuse modules, to enhance the multi-scale context information. Finally, in the UNet-style encoder–decoder framework, the ResNet model is adopted as the encoder. As for the decoder part, the multi-scale information obtained from our proposed AMFuse modules is hierarchically merged layer-by-layer to restore the feature map resolution for semantic segmentation. The experiments of RGBT multi-spectral semantic segmentation and salient object detection demonstrate the effectiveness of our proposed AMFuse module for fusing the RGB and thermal information.

A2TPNet: Alternate Steered Attention and Trapezoidal Pyramid Fusion Network for RGB-D Salient Object Detection

RGB-D salient object detection (SOD) aims at locating the most eye-catching object in visual input by fusing complementary information of RGB modality and depth modality. Most of the existing RGB-D SOD methods integrate multi-modal features to generate the saliency map indiscriminately, ignoring the ambiguity between different modalities. To better use multi-modal complementary information and alleviate the negative impact of ambiguity among different modalities, this paper proposes a novel Alternate Steered Attention and Trapezoidal Pyramid Fusion Network (A2TPNet) for RGB-D SOD composed of Cross-modal Alternate Fusion Module (CAFM) and Trapezoidal Pyramid Fusion Module (TPFM). CAFM is focused on fusing cross-modal features, taking full consideration of the ambiguity between cross-modal data by an Alternate Steered Attention (ASA), and it reduces the interference of redundant information and non-salient features in the interactive process through a collaboration mechanism containing channel attention and spatial attention. TPFM endows the RGB-D SOD model with more powerful feature expression capabilities by combining multi-scale features to enhance the expressive ability of contextual semantics of the model. Extensive experimental results on five publicly available datasets demonstrate that the proposed model consistently outperforms 17 state-of-the-art methods.

Weakly Supervised RGB-D Salient Object Detection With Prediction Consistency Training and Active Scribble Boosting

RGB-D salient object detection (SOD) has attracted increasingly more attention as it shows more robust results in complex scenes compared with RGB SOD. However, state-of-the-art RGB-D SOD approaches heavily rely on a large amount of pixel-wise annotated data for training. Such densely labeled annotations are often labor-intensive and costly. To reduce the annotation burden, we investigate RGB-D SOD from a weakly supervised perspective. More specifically, we use annotator-friendly scribble annotations as supervision signals for model training. Since scribble annotations are much sparser compared to ground-truth masks, some critical object structure information might be neglected. To preserve such structure information, we explicitly exploit the complementary edge information from two modalities (i.e., RGB and depth). Specifically, we leverage the dual-modal edge guidance and introduce a new network architecture with a dual-edge detection module and a modality-aware feature fusion module. In order to use the useful information of unlabeled pixels, we introduce a prediction consistency training scheme by comparing the predictions of two networks optimized by different strategies. Moreover, we develop an active scribble boosting strategy to provide extra supervision signals with negligible annotation cost, leading to significant SOD performance improvement. Extensive experiments on seven benchmarks validate the superiority of our proposed method. Remarkably, the proposed method with scribble annotations achieves competitive performance in comparison to fully supervised state-of-the-art methods.

A robust framework for shoulder implant X-ray image classification

Purpose

Medical images are increasingly popular; therefore, the analysis of these images based on deep learning helps diagnose diseases become more and more essential and necessary. Recently, the shoulder implant X-ray image classification (SIXIC) dataset that includes X-ray images of implanted shoulder prostheses produced by four manufacturers was released. The implant's model detection helps to select the correct equipment and procedures in the upcoming surgery.

Design/methodology/approach

This study proposes a robust model named X-Net to improve the predictability for shoulder implants X-ray image classification in the SIXIC dataset. The X-Net model utilizes the Squeeze and Excitation (SE) block integrated into Residual Network (ResNet) module. The SE module aims to weigh each feature map extracted from ResNet, which aids in improving the performance. The feature extraction process of X-Net model is performed by both modules: ResNet and SE modules. The final feature is obtained by incorporating the extracted features from the above steps, which brings more important characteristics of X-ray images in the input dataset. Next, X-Net uses this fine-grained feature to classify the input images into four classes (Cofield, Depuy, Zimmer and Tornier) in the SIXIC dataset.

Findings

Experiments are conducted to show the proposed approach's effectiveness compared with other state-of-the-art methods for SIXIC. The experimental results indicate that the approach outperforms the various experimental methods in terms of several performance metrics. In addition, the proposed approach provides the new state of the art results in all performance metrics, such as accuracy, precision, recall, F1-score and area under the curve (AUC), for the experimental dataset.

Originality/value

The proposed method with high predictive performance can be used to assist in the treatment of injured shoulder joints.

A multi model ensemble based deep convolution neural network structure for detection of COVID19

The year 2020 will certainly be remembered for the COVID-19 outbreak. First reported in Wuhan city of China back in December 2019, the number of people getting affected by this contagious virus has grown exponentially. Given the population density of India, the implementation of the mantra of the test, track, and isolate is not obtaining satisfactory results. A shortage of testing kits and an increasing number of fresh cases encouraged us to come up with a model that can aid radiologists in detecting COVID19 using chest Xray images. In the proposed framework the low level features from the Chest X-ray images are extracted using an ensemble of four pre-trained Deep Convolutional Neural Network (DCNN) architectures, namely VGGNet, GoogleNet, DenseNet, and NASNet and later on are fed to a fully connected layer for classification. The proposed multi model ensemble architecture is validated on two publicly available datasets and one private dataset. We have shown that our multi model ensemble architecture performs better than single classifier. On the publicly available dataset we have obtained an accuracy of 88.98% for three class classification and for binary class classification we report an accuracy of 98.58%. Validating the performance on private dataset we obtained an accuracy of 93.48%. The source code and the dataset are made available in the github linkhttps://github.com/sagardeepdeb/ensemble-model-for-COVID-detection.

Towards improving edge quality using combinatorial optimization and a novel skeletonize algorithm

BACKGROUND

Object detection and image segmentation of regions of interest provide the foundation for numerous pipelines across disciplines. Robust and accurate computer vision methods are needed to properly solve image-based tasks. Multiple algorithms have been developed to solely detect edges in images. Constrained to the problem of creating a thin, one-pixel wide, edge from a predicted object boundary, we require an algorithm that removes pixels while preserving the topology. Thanks to skeletonize algorithms, an object boundary is transformed into an edge; contrasting uncertainty with exact positions.

METHODS

To extract edges from boundaries generated from different algorithms, we present a computational pipeline that relies on: a novel skeletonize algorithm, a non-exhaustive discrete parameter search to find the optimal parameter combination of a specific post-processing pipeline, and an extensive evaluation using three data sets from the medical and natural image domains (kidney boundaries, NYU-Depth V2, BSDS 500). While the skeletonize algorithm was compared to classical topological skeletons, the validity of our post-processing algorithm was evaluated by integrating the original post-processing methods from six different works.

RESULTS

Using the state of the art metrics, precision and recall based Signed Distance Error (SDE) and the Intersection over Union bounding box (IOU-box), our results indicate that the SDE metric for these edges is improved up to 2.3 times.

CONCLUSIONS

Our work provides guidance for parameter tuning and algorithm selection in the post-processing of predicted object boundaries.

Rethinking Image Salient Object Detection: Object-Level Semantic Saliency Reranking First, Pixelwise Saliency Refinement Later

Human attention is an interactive activity between our visual system and our brain, using both low-level visual stimulus and high-level semantic information. Previous image salient object detection (SOD) studies conduct their saliency predictions via a multitask methodology in which pixelwise saliency regression and segmentation-like saliency refinement are conducted simultaneously. However, this multitask methodology has one critical limitation: the semantic information embedded in feature backbones might be degenerated during the training process. Our visual attention is determined mainly by semantic information, which is evidenced by our tendency to pay more attention to semantically salient regions even if these regions are not the most perceptually salient at first glance. This fact clearly contradicts the widely used multitask methodology mentioned above. To address this issue, this paper divides the SOD problem into two sequential steps. First, we devise a lightweight, weakly supervised deep network to coarsely locate the semantically salient regions. Next, as a postprocessing refinement, we selectively fuse multiple off-the-shelf deep models on the semantically salient regions identified by the previous step to formulate a pixelwise saliency map. Compared with the state-of-the-art (SOTA) models that focus on learning the pixelwise saliency in single images using only perceptual clues, our method aims at investigating the object-level semantic ranks between multiple images, of which the methodology is more consistent with the human attention mechanism. Our method is simple yet effective, and it is the first attempt to consider salient object detection as mainly an object-level semantic reranking problem.

Depth-Quality-Aware Salient Object Detection

The existing fusion-based RGB-D salient object detection methods usually adopt the bistream structure to strike a balance in the fusion trade-off between RGB and depth (D). While the D quality usually varies among the scenes, the state-of-the-art bistream approaches are depth-quality-unaware, resulting in substantial difficulties in achieving complementary fusion status between RGB and D and leading to poor fusion results for low-quality D. Thus, this paper attempts to integrate a novel depth-quality-aware subnet into the classic bistream structure in order to assess the depth quality prior to conducting the selective RGB-D fusion. Compared to the SOTA bistream methods, the major advantage of our method is its ability to lessen the importance of the low-quality, no-contribution, or even negative-contribution D regions during RGB-D fusion, achieving a much improved complementary status between RGB and D. Our source code and data are available online at https://github.com/qdu1995/DQSD.

RGB-D salient object detection: A survey

Salient object detection, which simulates human visual perception in locating the most significant object(s) in a scene, has been widely applied to various computer vision tasks. Now, the advent of depth sensors means that depth maps can easily be captured; this additional spatial information can boost the performance of salient object detection. Although various RGB-D based salient object detection models with promising performance have been proposed over the past several years, an in-depth understanding of these models and the challenges in this field remains lacking. In this paper, we provide a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail. Further, as light fields can also provide depth maps, we review salient object detection models and popular benchmark datasets from this domain too. Moreover, to investigate the ability of existing models to detect salient objects, we have carried out a comprehensive attribute-based evaluation of several representative RGB-D based salient object detection models. Finally, we discuss several challenges and open directions of RGB-D based salient object detection for future research. All collected models, benchmark datasets, datasets constructed for attribute-based evaluation, and related code are publicly available at https://github.com/taozh2017/RGBD-SODsurvey.