The aim of click-based interactive image segmentation is to obtain pixel-level segmentation masks by only a small number of manual clicks. This approach streamlines the process of pixel-level annotation and image editing. Much research has focused on this area. In particular, SimpleClick, which utilizes Vision Transformers, has implemented a straightforward design that has demonstrated its effectiveness in interactive image segmentation. However, two issues remain: First, this simple design does not fully utilize the global guidance provided by the interaction map. Second, treating all clicks equally fails to maximize the benefits of the new clicks’ guidance in each iteration. To address these challenges, we propose a novel interactive image segmentation network called Glclick. Specifically, we introduce a Global Hint Module (GHM) that integrates global information from clicks into the transformer backbone. In addition, Glclick incorporates a Local Correction Module (LCM) that performs local optimization on the target masks generated by the backbone network. Extensive experiments on four generic datasets and three medical datasets demonstrate the superiority and generalizability of Glclick. • Designed a brand-new interactive image segmentation model called “Glclick”. • Designed a Global Hint Module called GHM and a Local Correction Module called LCM. • Advanced performance was achieved on generic datasets and three medical datasets.

Referring camouflaged object detection (Ref-COD) is an emerging and challenging task that aims to localize camouflaged objects in complex scenes based on a small set of referring images with salient objects. However, existing methods primarily focus on semantic alignment between the referring and camouflaged objects while overlooking scale discrepancies, leading to under-response when small references guide large objects and over-response when large references guide small ones. To overcome this limitation, we propose a novel Multi-scale Interaction Network (MINet), explicitly designed to handle feature interactions across different scales in Ref-COD. MINet begins with a Dual-Source Fusion Block (DSFB) for semantic fusion between the referring and camouflaged features. Then, the Intra-scale Interaction Block (IIB) enhances local saliency within each scale by modeling contextual importance. Next, the Cross-scale Interaction Block (CIB) performs offset-guided alignment to bridge spatial gaps in multiscale feature fusion. Finally, the Cross-scale Aggregation Decoder (CAD) integrates multiscale features, effectively decoding the aggregated information to produce accurate predictions. Extensive experiments on Ref-COD datasets demonstrate that our method achieves state-of-the-art performance, highlighting the importance of scale interaction in Ref-COD.

Camouflaged object detection involves identifying camouflaged objects visually blended into the surroundings, holding crucial significance in various visual applications. Existing methods primarily focus on leveraging boundary information to enhance camouflaged object detection. However, they often overlook the background interference near the object boundaries, which leads to coarse boundary predictions and results in suboptimal detection performance. In this paper, to address this problem, we propose GBNet, a gated boundary-aware network designed to enhance boundary precision and improve overall detection performance. Specifically, GBNet incorporates a boundary-enhanced module that selectively filters extraneous background information through a boundary gate block, ensuring the generation of high-quality boundary information. Additionally, a boundary-aware decoder is designed to enrich the representation ability of the decoder by injecting high-quality boundary features and aggregating contextual features. With meticulous design, GBNet excels in accurately segmenting camouflaged objects in challenging scenarios. Extensive experiments demonstrate that GBNet outperforms 19 state-of-the-art methods significantly across four widely-used benchmark datasets. The source code is publicly available at https://github.com/wooownn/GBNet.

Recently, Transformer-based few-shot classification methods are widely exploited. However, they only leverage feature information at a single scale, resulting in weak feature representations, which cannot fully capture the rich information contained in a limited number of images regarding diverse objects with different scales, even those belonging to the same category. To mitigate this issue, we propose a multi-scale feature sets matching scheme in vision Transformer for few-shot classification, and name it FSViT, which can sufficiently extract discriminative features from the few number of labeled support examples. Concretely, we establish a patch-based multi-scale feature representation based on the feature extractors of FSViT, where we introduce an attention-aware grid pooling operation to merge adjacent patches with various scales to obtain multi-scale feature sets. Moreover, we devise a multi-scale patch matching metric to aggregate the measurement of similarity over the multi-scale feature sets for few-shot classification. Extensive experiments demonstrate the effectiveness of the proposed FSViT in both 1-shot and 5-shot scenarios on standard single-domain and cross-domain few-shot classification, especially improving the state-of-the-art recognition accuracy by 1.27% and 1.33% on average on the Mini-ImageNet and CFAIR-FS datasets, respectively. The code of FSViT is available athttps://github.com/codeshop715/FSViT.

Accurate recognition of marine species in drone-captured images is essential in maintaining the stability of coastal zone ecosystems. Unmanned aerial vehicle (UAV) remote sensing images usually lack paired supervised signals and suffer from color distortion and blurring due to the interaction of ambient light with cross-medium transmission between air and water. However, current algorithms mainly focus on supervised training methods and also ignore the interaction involved in the cross-medium transmission of light in water. In this article, for UAV in coastal zones, we propose an unsupervised image water removal model, named DewaterGAN, which is based solely on low-tide and high-tide images without paired supervised signals and also preserves color and texture in the water removal process. Specifically, our approach involves two key steps: an unsupervised training CycleGAN network accomplishes domain transitions from low-tide level to high-tide level, and a physics-based attention module guides image water removal and maintains authenticity. Additionally, we utilize evaluation metrics of image restoration peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) to quantitatively analyze the performance of the model. We also employed several non-reference metrics (UIQM, UCIQE, NIQE, BRISQUE, LIQE, ILNIQE, and CLIPIQA) to evaluate the visual quality of the image de-watering process. Extensive experiments conducted on both our water removal dataset and public datasets validate the efficacy of our model. The code is athttps://github.com/yfq-yy/Dewater.git.

The critical challenge of video object counting is to avoid counting the same object multiple times in different frames. By comparing the appearance and motion feature information of the detection results, the authors use the multi-object tracking method to assign an independent ID number to each object. From the time the ID tag is obtained until the end of the video, each object is counted only once. However, even minor amounts of image noise can cause irreversible changes in feature information, resulting in severe tracking drifts. This paper introduces the concept of scene awareness and addresses unreasonable ID assignment caused by unreliable feature matching in the context of region division. Through the macro analysis of the scene, the authors define the region (called the transition region) where the number of objects can increase or decrease and require that all ID assignments for new objects and ID deletions for existing objects take place only in the transition region. Because the actual number of objects in the non-transition region is constant, they rematch unmatched objects with existing IDs in the region (called ID relocation) because changes in object ID are caused by feature matching failure. In this paper, the authors create algorithms for dynamically generating transition regions, detecting object increases and decreases, and relocating object IDs. Experimental results show that the method effectively improves the accuracy of video object counting.