The low storage and strong representation capabilities of hash codes for image retrieval has made hashing technologies very popular. Several existing deep hashing methods focus on the task of general image retrieval, while neglecting the task of fine-grained image retrieval. Recently, some fine-grained hashing methods have been proposed to capture the subtle differences, which mainly utilize the single-modality visual features to solve the discriminative region localization while ignoring the semantic information. In this paper, we propose a correlation filtering hashing (CFH) method to learn discrete binary codes, which can adequately take advantage of the cross-modal correlation between the semantic information and the visual features for discriminative region localization. Specifically, we utilize a feature pyramid network to learn multi-level visual features. Subsequently, the label vector is embedded into the visual space, which can be used as a correlation filter on the feature maps to capture the latent location of objects. Finally, we perform global average pooling over the output maps and concatenate the features of different levels to produce the hash codes of query images. Extensive experiments on two fine-grained datasets show that the proposed CFH outperforms the state-of-the-art hashing methods.

Despite the high demand for Internet location service applications, Wi-Fi indoor localization often suffers from time- and labor-intensive data collection processes. This study proposes a novel indoor localization model that utilizes fingerprinting technology based on a convolutional neural network to address this issue. The aim is to enhance Wi-Fi indoor localization by streamlining the data collection process. The proposed indoor localization model leverages a 3D ray-tracing technique to simulate the wireless received signal strength intensity (RSSI) across the field. By incorporating this advanced technique, the model aims to improve the accuracy and efficiency of Wi-Fi indoor localization. In addition, an RSSI heatmap fingerprint dataset generated from the ray-tracing simulation is trained on the proposed indoor localization model. To optimize and evaluate the model’s performance in real-world scenarios, experiments were conducted using simulated datasets obtained from the publicly available databases of UJIIndoorLoc and Wireless InSite. The results show that the new approach solves the problem of resource limitation while achieving a verification accuracy of up to 99.09%.

Salient object detection (SOD) task for optical remote sensing images (RSIs) plays an important role in many remote sensing applications. Most of the existing methods train their networks depending on a large amount of pixel-wise datasets. However, such expensive and time-consuming training setting prevents the approaches becoming flexible and scalable solutions. To this end, we explore efficient SOD for optical RSIs based on easily accessible weak supervision source. In this work, we propose a novel end-to-end progressive attention-based feature recovery framework with scribble supervision. Specifically, to better locate challenging salient objects in optical RSIs, an object position module (OPM) is proposed to capture and enhance the long-range semantic dependence of objects’ position information, which depends on the complementary attention mechanism. Also, to restore the entire salient objects, a context refinement module (CRM) is proposed, which extract local contextual information for better propagating high-level semantics to low-level details. Moreover, to improve the adaptability of the network to the changing scenarios of optical RSIs, we propose a salient region correcting (SRC) mechanism to help the predicted salient regions rectify their saliency values by constraining the saliency relationship between predictions from different augmentation models. In addition, due to the lack of dataset for weakly supervised SOD for optical RSIs, we relabeled an existing large-scale optical RSIs dataset with scribbles, namely, EORSSD-S. Experimental results on benchmark datasets demonstrate that the proposed method can outperform other weakly supervised SOD methods. Also, the proposed method even outperformed some fully supervised methods. https://github.com/melonless/PAFR .

Mask is considered as an important prior for fusion, which could selectively enhance specific regions to generate ideal fused images. However, masks used in the existing methods exhibit limitations in the precise representation of targets, and more importantly, these masks are generated from a single modality, which restricts the effective integration of multi-modal information. To address this issue, we propose a competitive mask-guidance fusion method for infrared and visible images. A multi-modal semantic-sensitive mask selection network is proposed to generate complementary-mask maps, which organically integrate advantageous target regions of different modalities by competitively comparing the qualities of masks. In this network, a pseudosiamese architecture is designed to obtain respective target masks, and specifically, a spatial-aligned-based feature aggregation module is devised to produce high-quality pseudo-labels which are served as references for the generation of the complementary-mask maps. Furthermore, we propose a bidirectional-collaboration region fusion strategy, which enhances the expression of advantageous target regions from each modality in foreground while suppressing the contribution of corresponding regions from the other modality in background. Compared to methods on public datasets, the results show that our method significantly enhances the description of semantic-sensitive targets in fused images, including the saliency and the integrity of structural information. Code are available at https://github.com/9DunDun9/FusionNet.git.

The inconsistency in the feature spaces of cross-modality images makes it challenging to adaptively fuse images of different modalities. The fusion rules inevitably have global or local proneness towards one modality. To address the challenge, this paper proposes a novel fusion method based on dual-cycle crosswise awareness and global structure-tensor preservation, which is a modal transition network and contrives images taking part in the fusion operation to have similar feature spaces. Firstly, a dual-cycle modality transition network (DMT) is proposed. Under the guidance of cross-aware-based adversarial learning and the constraints of edge prior, it allows the generated images better inherit the specialties of original images on the basis of pursuing the modal transition. Secondly, a set of global structure-tensor preserving models (STPs) and STP-aware loss are designed to enhance the capabilities of the network in structural preservation and modal consistency perception. STP-aware loss, collaborate with cycle-consistency loss and cross-aware loss, enable our network to effectively supervise the generation of high-quality pseudo images and to eliminate the adverse artifacts and structural degradation. Thirdly, we devise a progressively adaptive fusion network (PAF), which sequentially generates pairwise images with unified modalities and fine-tunes their structures to overcome the challenge of effective aggregation of different modal attributes. Extensive comparative experiments demonstrate that our CASPFuse outperforms state-of-the-art fusion methods in adequately expressing the advantageous complementary information of different modalities.

Surface defect detection plays a quality assurance role in industrial manufacturing processes. However, the diversity of defects and the presence of complex backgrounds bring significant challenges to salient object detection. To this end, this study proposes a new adaptive multi-scale feature fusion network (AMSFF-Net) to solve the SOD problem of object surface defects. The upsampling fusion module used adaptive weight fusion, global feature adaptive fusion, and differential feature adaptive fusion to fuse information of different scales and levels. In addition, the spatial attention (SA) mechanism was introduced to enhance the effective fusion of multi-feature maps. Preprocessing techniques such as aspect ratio adjustment and random rotation were used. Aspect ratio adjustment helps to identify and locate defects of different shapes and sizes, and random rotation enhances the ability of the model to detect defects at different angles. The negative samples and non-uniform-distribution samples in the magnetic tile defect dataset were further removed to ensure data quality. This study conducted comprehensive experiments, demonstrating that AMSFF-Net outperforms existing state-of-the-art technologies. The proposed method achieved an S-measure of 0.9038 and an $F_{\mathsf{\beta }}^{\mathrm{m}\mathrm{a}\mathrm{x}}$ of 0.8782, which represents a 1% improvement in $F_{\mathsf{\beta }}^{\mathrm{m}\mathrm{a}\mathrm{x}}$ compared to the best existing methods.