Underwater object detection suffers from limited long-range dependency modeling, fine-grained feature representation, and noise suppression, resulting in blurred boundaries, frequent missed detections, and reduced robustness. To address these challenges, we propose the Mamba-Driven Feature Pyramid Decoding framework, which employs a parallel Feature Pyramid Network and Path Aggregation Network collaborative pathway to enhance semantic and geometric features. A lightweight Mamba Block models long-range dependencies, while an Adaptive Sparse Self-Attention module highlights discriminative targets and suppresses noise. Together, these components improve feature representation and robustness. Experiments on two publicly available underwater datasets demonstrate that MFPD significantly outperforms existing methods, validating its effectiveness in complex underwater environments. The code is publicly available at:https://github.com/YitengGuo/MFPD

Multi-object tracking (MOT) has garnered considerable attention due to its relevance in practical applications such as automated devices in smart cities. However, under complex conditions, existing trackers often fail to accurately capture or characterize target motion patterns, exhibiting limitations in flexibility and interpretability. To address these challenges, this paper introduces CHTracker, a confidence-guided hierarchical association paradigm for MOT. By integrating spatial features with varying confidence levels, CHTracker enhances the granularity of motion pattern modeling in edge-case scenarios where conventional trackers are prone to association ambiguity. Our paradigm adaptively utilizes distinct tracking cues and assignment metrics tailored to hierarchical target structures, thereby enabling collaborative tracking. Additionally, CHTracker incorporates the diagonal length of the target bounding box as a state variable during position prediction, which significantly improves the robustness against diverse motion noise. Extensive experimental results on multiple benchmarks, including Dance-Track, MOT17, MOT20, and Singapore Maritime Dataset (SMD), demonstrate that CHTracker achieves the state-of-the-art performance in accuracy, robustness, and generalization. Furthermore, our association paradigm is extended to a visible-infrared fusion version for evaluation on the multimodal CAMEL dataset, underscoring its practical potential to fulfill heterogeneous modality requirements in real-world scenarios. Our code will be available at https://github.com/ZyanChenyang/CHTracker.

Single underwater image often suffer from severe quality degradation and field-of-view limitation due to the underwater light propagation characteristics and the viewing range of camera equipment. To address these challenges, we propose a underwater scene clarity reconstruction framework called USCR, which comprises a multilayer information fusion (MIF) method for underwater image enhancement (UIE) and a self-organized stitching (SOS) method for image stitching. First, MIF corrects color distortion, enhances contrast, and highlights image detail information through a minimally attenuated channel guided color correction strategy and a gradient weight fusion strategy. Subsequently, SOS is applied to stitch the enhanced underwater images, which utilizes a homography matrix to initially stitch the image sequence, and further employs a pixel blending strategy based on boundary distance weighting for boundary pixel fusion to the initial stitch image, aiming to ensure a homogeneous transition of the stitch region. Our reconstructed underwater scenes are characterized by visual clarity and a wide field-of-view. Extensive qualitative and quantitative experimental validations show that USCR outperforms the state-of-the-art methods in underwater visual reconstruction task.

Light propagation underwater is susceptible to wavelength attenuation and scattering, leading to degradation plagued by color distortion, contrast degradation, and reduced visibility in underwater imaging. To handle the degradations, the paper proposes an underwater image enhancement method via advantage feature weighted fusion, called AFWF. Specifically, we propose a three-channel contrast enhancement strategy that effectively reduces the color distortion of a raw input image via a three-channel adaptive color compensation strategy. Meanwhile, we employ a fast exposure fusion to integrate the image sequences obtained from the multi-scale gamma correction and adaptive contrast enhancement strategies to improve the global contrast of the above-mentioned image. Subsequently, a single-channel contrast enhancement is proposed to improve the local contrast and edge detail information by enhancing the multi-level details of the raw image. Finally, we adopt the advantage feature weighted fusion strategy to analyze and selectively fuse the advantage feature of different enhanced images layer by layer to reconstruct a high-quality result. Extensive experimental verification results highlight that our AFWF method is superior to the state-of-the-art (SOTA) methods in improving raw underwater images’ color, contrast, and detail. The code is publicly available at: https://www.researchgate.net/publication/393021384_2025-AFWF.

Using image-level weakly supervised semantic segmentation (WSSS) techniques to segment tissue regions in giga-pixel histopathological whole slide images (WSI) has garnered widespread attention, as it can reduce many annotation workloads for pathologists. Most recent studies are based on class activation mapping (CAM) to generate pseudo masks, which are then used to train segmentation model in a fully supervised manner. However, it is still a challenge to accurately segment non-predominant tissue categories due to the existence of long-tailed and inter-class homogeneity matters. For these matters, we propose three designs to solve them: 1) Diffusion-based Data Generation to synthesis new images of tail class to expand data distribution; 2) Feature Recalibration to reassign the logits in CAM to narrow the feature-level prediction gap between predominant and non-predominant classes; 3) Grade-skip Learning to correct the under-fitting tendency of hard samples during the segmentation phase. Moreover, we also design a powerful pipeline LoHo for histopathology tissue segmentation. Extensive experiments demonstrate that our method not only achieves new state-of-the-art performances but also significantly improves segmentation of tail classes. In addition, our methods are plug-and-play, making it easily integrable into many mainstream WSSS frameworks.

Underwater images often suffer from visual degradation due to varying light absorption at different wavelengths and scattering from suspended particles. To tackle these issues, we present an intelligent optimized multi-exposure image fusion method called IMIF. Specifically, we propose an adaptive color transfer strategy that employs a colorless reference image to correct the color distortion issue by transferring the mean and standard deviation of the reference image to adjust a color-balanced image. Subsequently, we introduce a particle swarm optimization algorithm that intelligently selects the optimal set of exposure image sequences by employing information entropy and edge intensity of the image as fitness metrics. Meanwhile, we leverage a guided filtering strategy to decompose the exposure image sequences into basic and detailed layers, taking into account the exposure characteristics of each layer to generate corresponding weight maps. Finally, we employ a multi-exposure fusion strategy to adaptively fuse the exposed image sequences with weight maps, producing an enhanced result. Extensive experiments conducted on three datasets demonstrate that our IMIF method outperforms state-of-the-art (SOTA) methods in both qualitative and quantitative evaluations. Additionally, the enhanced results produced by our proposed IMIF method significantly improve the accuracy of object detection and keypoint detection. The is available at https://www.researchgate.net/publication/403951386_2026-IMIF.

Semi-supervised segmentation (S3) is one of the preferred choices for histopathological image segmentation tasks, while how to improve model’s learning capability for unlabeled data remains a key challenge in S3. The remarkable feature extraction abilities of Segment Anything Model (SAM) offers a potential opportunity. However, SAM’s performance on contextual complex histopathological images is not so desirable due to its limitations in finely capture structural relationships. To address this issue, we propose a novel SAM-based S3framework QuPaS, which consists of Quantum Force Field (QFF) Finetuning and Adversarial Estimation (AE). QFF covers the shortage of SAM’s limited understanding of spatial structure by simulating intermolecular forces to explore the structural topological relationships between pixel-level features. AE introduces an adversarial estimation network to align the consistency of confidence distributions between different outputs, thereby reducing the interference of incompatible semantic features on the model. Extensive experiments across three challenging histopathological segmentation scenarios have demonstrate that our QuPaS completely outperforms the state-of-the-art S3methods. Furthermore, QuPaS is able to maintain stable generalization performance on previously unseen domains. The code will be released at: https://github.com/director87/QuPaS.

Recently, Transformer-based approaches have emerged as powerful tools for hyperspectral image (HSI) classification. HSI inherently exhibits low-rank and sparse properties due to spatial continuity and spectral redundancy. However, most existing methods directly adopt standard Transformer architectures, overlooking the distinctive priors inherent in HSI, which limits the classification performance and modeling efficiency. To address these challenges, this paper proposes a Multi-scale Low-rank and Sparse Transformer (MLSFormer) that effectively integrates both low-rank and sparse priors. Specifically, we leverage tensor low-rank decomposition (TLRD) to factorize the query, key, and value matrices into low-rank tensor products, capturing dominant low-rank structures. In parallel, we introduce a sparse attention mechanism to retain only the most important connections. Furthermore, a multi-scale attention mechanism is designed to hierarchically partition attention heads into global, medium, and local groups, each assigned tailored decomposition ranks and sparsity ratios, enabling comprehensive multi-scale feature extraction. Extensive experiments on three benchmark datasets demonstrate that MLSFormer achieves superior classification performance compared to state-of-the-art methods.

Due to the complex physical environment underwater, underwater captured images often suffer from issues such as color distortion, low contrast, and loss of texture details. To address this issue, we propose a color channel matching (CCM) method for underwater optical image contrast enhancement, called CCM. Specifically, we first convert the raw image into a grayscale image and employ histogram matching techniques to make the brightness distribution of the image more uniform, thereby reducing brightness variations caused by environmental factors. Then, we transform the matched image into the hue-saturation-intensity (HSI) color space and optimize the HSI channels separately. During this process, we decouple the intensity information from the color information to avoid interference during enhancement, which employs adaptive histogram equalization on the intensity channel to improve contrast and detailed representation further. Finally, we fuse the processed intensity channel with the optimized hue and saturation channels to obtain the final contrast-enhanced image. Extensive qualitative and quantitative experimental results demonstrate that the proposed method exhibits strong robustness and generalization capabilities in enhancing the contrast of underwater images.

Underwater images encounter a range of quality degradation issues caused by the differential scattering and absorption of light in water. To address these challenges, we introduce a WFAC method, a wavelet decomposition fusion method that combines global and local contrast for underwater image enhancement. Specifically, we begin with a color transfer compensation strategy to correct the colors in a degraded underwater image. Subsequently, we utilize the pixel gradient distribution to create a matrix weight map that dynamically adjusts the weight distribution in overly bright or dark areas of the color-corrected image, enhancing its global contrast. Simultaneously, we apply a rapid integration statistical strategy to adaptively fine-tune the local contrast of color-corrected images using the local mean and variance statistics. To combine the strengths of various enhanced images, we implement a wavelet decomposition fusion strategy to break down different scale components of globally and locally contrast-enhanced images and merge the benefits of varying scale images to obtain a high-quality underwater image. Comprehensive experimental assessments across three underwater image datasets demonstrate that our WFAC method efficiently recovers colors and boosts contrast in degraded underwater images. The code is publicly available at:https://www.researchgate.net/publication/386508762_2024WFAC.

Underwater operations frequently encounter turbid environments, where light absorption and scattering by suspended particles degrade image quality by causing color distortion, uneven brightness, and blurred details. Clear imaging in such conditions is essential for enhancing the efficiency and effectiveness of underwater tasks, including exploration, marine ecological monitoring, and the preservation of underwater cultural heritage. However, existing underwater image enhancement methods struggle to perform well in turbid waters, especially in highly turbid conditions. In this study, we present an advanced method designed to significantly improve the clarity of images captured in turbid water. We begin by introducing an adaptive color correction algorithm that uses the dominant color channel’s pixel values to adjust and restore the colors of other channels, mitigating color distortion in turbid conditions. Subsequently, we apply adaptive threshold segmentation and turbidity assessment to automatically calibrate histogram equalization, which enhances local contrast and suppresses noise. Finally, we develop a dark channel prior based on turbidity background light estimation, which further improves color restoration and detail recovery. Our proposed method outperforms existing state-of-the-art techniques in color restoration, turbidity removal, and detail enhancement. Experimental results demonstrate that our approach effectively enhances imaging performance in turbid waters, thereby significantly improving the operational efficiency of various underwater applications.

Object detection methods using deep convolutional neural networks (CNNs) have derived major advances in normal images. However, such success is hardly achieved with adverse weather due to a lack of visibility . To tackle this problem, we propose a Multi-scale Adaptive Sampling Fusion Network, named MASFNet. In this paper, we design a Feature Adaptive Enhancement Network (FAENet) consisting of three modules to adaptively perform feature enhancement on feature maps in adverse scenarios. These modules in FAENet are integrated by the Laplace pyramid, which can perform receptive field fusion, attention perception, and affine transformation for image feature enhancement. To improve the detection performance, we propose a Multi-scale Sampling Fusion Pyramid Network (MSFNet), which is capable of fusing different scale features to improve the semantic information. Experimental results demonstrate that MASFNet achieves 73.68% and 30.95% mAP on the real scene fog dataset (RTTS) and foggy driving dataset (FDD) respectively. Additionally, on the real-world scenario low illumination dataset (ExDark), MASFNet attains a substantial mAP of 63.80%, surpassing current state-of-the-art object detectors while retaining lightweight and high-speed. The source code will be released at https://github.com/PolarisFTL/MASFNet.

Hyperspectral remote sensing plays an important role in agricultural monitoring, and fine-grained wheat variety classification is essential for advancing smart agriculture. However, progress is limited by the scarcity of high-quality spectral samples and the challenges associated with collecting large-scale hyperspectral data. To cope with these issues, we design a hybrid supervised-driven two-stream collaborative network (HSTNet), which consists of a semi-supervised conditional generative adversarial network for data augmentation (SCGAN) and a supervised two-stream discriminative network (STDNet) for wheat classification. In SCGAN, the generator constructs a mapping relationship between input noise and real wheat hyperspectral samples to generate fake wheat hyperspectral samples that are highly matched with the distribution of the real sample, and the discriminator with multilayer perceptions utilizes discriminative learning to identify real and fake samples. In STDNet, it collaboratively extracts the spectral, spatial and texture features of wheat hyperspectral images employing the dual-stream branch structure of 3DCNN and 2DCNN. Subsequently, it utilizes the Fast Fourier Transform and the cross-attention mechanism to refine and fuse these features to improve their capability of feature expression. Noteworthy, the individual design effectively improves the classification results of wheat varieties via collaborative optimization among modules. Besides, we built a mixed wheat hyperspectral dataset (MWHD) with 4800 samples of 20 wheat varieties. Extensive experiments on our constructed MWHD dataset demonstrate that the proposed HSTNet outperforms state-of-the-art methods in wheat variety classification. The code is publicly available at: https://github.com/bakam412/HSTNet.

The most significant characteristic of long-tailed classification is that severe sample imbalance causes the model to be biased towards the head category. While the long-tailed distribution of multimedia dataset remains a constant, we can enhance the acquisition of balanced training samples and corresponding features during the learning process. This paper innovatively designs a sample provider to construct balanced training samples to enhance the acquisition of comprehensive features, and proposes a Siamese-based parameter-sharing framework to handle data with long-tailed distributions. Specifically, one branch of the Siamese network is introduced to classify samples with conventional random cropping sampling, another branch integrates the advantages of constructed balanced samples and hybrid optimization to capture the balanced features to identify more precise category boundaries. This combination not only facilitates the learning of long-tailed distribution but also strengthens the model's extraction of balanced features through the incorporation of contrastive learning. Most significantly, extensive experiments on CIFAR10-LT, CIFAR100-LT, ImageNet-LT and iNaturalist 2018 datasets demonstrate our model not only achieves superior performance but also retains the benefits of end-to-end training. Specifically, our method achieves 60.7% accuracy on ImageNet-LT with an end-to-end ResNeXt-50 backbone.

Underwater images widely endure severe color distortion because of the absorption and scattering of the water medium. We present a zero-approximation principle for underwater image color correction, called ZAP, to tackle this issue. Specifically, we first present the channel’s a and b pixel values to subtract the corresponding channels’ average pixel values so that the histograms corresponding to their pixel values are symmetric about the zero within the CIELab model. Afterward, we utilize the standard deviation of the channels’ a and b compensated pixel values to adjust the channels’ dynamic range and correct the image color distortion. Broad qualitative and quantitative experiments prove the practicability of ZAP for correcting color distortion in underwater images.

Underwater images often reveal color distortion and poor visibility due to light propagation in water being affected by the selective absorption and scattering of suspended particles. This letter presents an efficient color channel transfer (CCT) method that largely restores color distortion and improves visibility of underwater images. Any captured underwater image with at least one color channel is highly attenuated in real underwater imaging. To compensate for the loss of information in the attenuated channel, the CCT transfers the degraded image to the CIELab color space and compensates for the loss of information in the degraded image by adjusting luminance and chrominance. The reference values of the color transfer image are statistically calculated from many high-quality images to ensure a relatively balanced color distribution. Extensive experiments on three underwater image datasets show that after applying our CCT, the enhancement method leads to satisfactory results in both metric scores and runtimes.

Due to the complex imaging mechanism, underwater images often suffer from multiple degradation issues, such as color cast, blurry detail, and low contrast, which affect the extraction of valuable information. To deal with these degradation issues, a simple yet effective underwater image quality improvement method based on color, detail and contrast restoration (CDCR) is developed, which consists of three key modules: a well-preserved finding-driven color balance module (CBM), a linear saturation transformation-based discriminant function-based detail restoration module (DRM), and a transmission minimization-oriented contrast restoration module (CRM). First, the CBM explores a well-preserved channel finding and employs a channel compensation strategy to balance the color differences among three color channels. Second, the DRM uses a piecewise underwater image saturation estimation strategy, which takes the various spectral properties of water into account and designs an additional linear saturation transformation-based discriminant function to prevent the transmission from being under-estimated. At last, the CRM estimates a global backscatter light based on transmission minimization and further improves the contrast by locally removing the backscatter light of the base layer. Our restored image is appealing in its natural color, fine details, and high contrast. Extensive experiments on three underwater image enhancement datasets show that our CDCR achieves better results than state-of-the-art methods, i.e., compared with the second-best method, the average PCQI and UIQM values of our method increase by 5.7% and 0.2%, and the average Blur and DFAD values of our method decrease by 8.0% and 5.3%. Meanwhile, experiments further suggest that the rate of new visible edges and the quality of contrast restoration of our CDCR at least increase by 7.7% and 51.2% in most tested sandstorm and foggy images, respectively, which demonstrates that our method has a good generalization capability for sandstorm and foggy image restoration.

Underwater imaging systems have evolved into essential hardware equipment for developing and utilizing marine resources. However, the complex underwater physical environment has often led to severe quality degradation of underwater visual perception. To address these issues, we design a principal component fusion method of foreground and background to enhance an underwater image, named PCFB. Specifically, we present a color balance-guided color correction strategy to remove color distortion issues that equalize the pixel values of the a and b channels of the CIELab color model. Subsequently, we implement a percentile maximum-based contrast enhancement strategy and a multilayer transmission map estimated dehazing strategy on the color-corrected image to yield the contrast-enhanced foreground and dehazed background sub-images. Finally, we employ a principal component analysis fusion method to reconstruct a high-visibility underwater image by integrating the advantages of the foreground contrast-enhanced sub-image and the background dehazed sub-image. Comprehensive experiments on three datasets demonstrate that our PCFB surpasses state-of-the-art methods both qualitatively and quantitatively. Moreover, our PCFB exhibits outstanding generalization capabilities for addressing haze and low-light images. The code is publicly available at:https://www.researchgate.net/publication/381259520_2024-PCFB.

Underwater images typically suffer from various quality degradation issues due to the scattering and absorption of light, but these degraded-quality underwater images are unbeneficial for analysis and applications. To effectively solve these quality degradation issues, an underwater image enhancement method via weighted wavelet visual perception fusion is introduced, called WWPF. Concretely, we first present an attenuation-map-guided color correction strategy to correct the color distortion of an underwater image. Subsequently, we employ the maximum information entropy optimized global contrast strategy to the color-corrected image to obtain a global contrast-enhanced image. Meanwhile, we apply a fast integration optimized local contrast strategy to the color-corrected image to get a local contrast-enhanced image. To exploit the complementary of the global contrast-enhanced image and the local contrast-enhanced image, we introduce a weighted wavelet visual perception fusion strategy to obtain a high-quality underwater image by fusing the high-frequency and low-frequency components of images at different scales. Our extensive experiments on three benchmarks validate that our WWPF outperforms the state-of-the-art methods in qualitative and quantitative. Besides, the underwater images processed by our WWPF also benefit practical underwater applications. The code is availablehttps://github.com/Li-Chongyi/WWPF_code.

Self-supervised learning (SSL) has demonstrated its power in generalized model acquisition by leveraging the discriminative semantic and explicit positional information of unlabeled datasets. Unfortunately, mainstream contrastive learning-based methods excessive focus on semantic information and ignore the position is also the carrier of image content, resulting in inadequate data utilization and extensive computational consumption. To address these issues, we present an efficient SSL framework, learning What and Where to learn (W2SSL), to aggregate semantic and position features. Concretely, we devise a spatially-coupled sampling manner to process images through pre-defined rules, which integrates the advantage of semantic (What) and positional (Where) features into framework to enrich the diversity of feature representation capabilities and improve data utilization. Besides, a spectrum of latent vectors is obtained by mapping the positional features, which implicitly explores the relationship between these vectors. Whereafter, the corresponding discriminative and contrastive optimization objectives are seamlessly embedded in the framework via a cascade paradigm to explore semantic and positional features. The proposed W2SSL is verified on different types of datasets, which demonstrates that it still outperforms state-of-the-art SSL methods even with half the computational consumption. Code will be available at https://github.com/WilyZhao8/W2SSL.

Wheat variety identification from hyperspectral images holds significant importance in both fine breeding and intelligent agriculture. However, the discriminatory accuracy of some techniques is limited due to insufficient datasets, data redundancy, and noise interference. To address these issues, we propose a wheat variety identification framework called generate adversarial-driven cross-aware network (GACNet), comprising a semi-supervised generative adversarial network (GAN) for data augmentation and a cross-aware attention network (CAANet) for variety identification. First, the semi-supervised GAN (SSGAN) alleviates data scarcity by generating fake hyperspectral images as realistically as possible through learning the distribution hypothesis of real hyperspectral images, while the discriminator distinguishes between real and fake hyperspectral images. Subsequently, the CAANet is employed for wheat variety identification, which leverages a cascading cross-learning of 3-D and 2-D convolutions to fully exploit spectral, spatial, and texture features and refines the features through an embedded attention mechanism in the cross-convolutional module. Additionally, we constructed a hyperspectral wheat variety dataset (HWVD) comprising 4560 samples of 19 categories. Extensive experiments on our dataset demonstrate that our GACNet outperforms state-of-the-art methods for wheat variety identification. The HWVD will be made available.

In this paper, we present a ranking-based underwater image quality assessment (UIQA) method, abbreviated as URanker. The URanker is built on the efficient conv-attentional image Transformer. In terms of underwater images, we specially devise (1) the histogram prior that embeds the color distribution of an underwater image as histogram token to attend global degradation and (2) the dynamic cross-scale correspondence to model local degradation. The final prediction depends on the class tokens from different scales, which comprehensively considers multi-scale dependencies. With the margin ranking loss, our URanker can accurately rank the order of underwater images of the same scene enhanced by different underwater image enhancement (UIE) algorithms according to their visual quality. To achieve that, we also contribute a dataset, URankerSet, containing sufficient results enhanced by different UIE algorithms and the corresponding perceptual rankings, to train our URanker. Apart from the good performance of URanker, we found that a simple U-shape UIE network can obtain promising performance when it is coupled with our pre-trained URanker as additional supervision. In addition, we also propose a normalization tail that can significantly improve the performance of UIE networks. Extensive experiments demonstrate the state-of-the-art performance of our method. The key designs of our method are discussed. Our code and dataset are available at https://li-chongyi.github.io/URanker_files/.

This letter proposes an effective underwater image restoration method that consists of a local image descattering and an adaptive brightness improvement. First, we establish an adaptive objective function for improving the brightness of underwater image according to the best-preserved channel of an image, and an augmented Lagrange multiplier based alternating direction minimization algorithm is derived to solve the optimization problem. Second, we introduce a local transmission estimation method that takes into account the different attenuation of light on the red, green and blue channels, which overcomes the limitation that existing methods heavily depend on the global transmission over the entire image. Extensive experiments on real-world underwater images demonstrate the effectiveness of the proposed method in underwater image restoration. Moreover, our method shows good generalization capability for enhancing remote sensing and nighttime images.

Due to the absorption and scattering of light, underwater captured images often face serious quality degradation issues. In this letter, we propose to cope with the aforementioned issues via piecewise color correction and dual prior optimized contrast enhancement. Specifically, we first present the piecewise color correction method using the maximum mean and two gain factors to correct the color cast of each color channel. Then, we propose a dual prior optimized contrast enhancement method, which relies on the spatial and texture priors to decompose the base layer and detail layer of the V channel in HSV color space. Meanwhile, we employ different enhancement strategies in different layers to enhance the contrast and texture detail of underwater images. Our extensive experiments on several benchmark datasets show that our method outperforms eleven compared state-of-the-art methods. Moreover, our method has good generalization capability for fog and low-light images. The code is available athttps://github.com/Li-Chongyi/PCDE.

Self-supervised representation learning (SSL) typically suffers from inadequate data utilization and feature-specificity due to the suboptimal sampling strategy and the monotonous optimization method. Existing contrastive-based methods alleviate these issues through exceedingly long training time and large batch size, resulting in non-negligible computational consumption and memory usage. In this paper, we present an efficient self-supervised framework, called GLNet. The key insights of this work are the novel sampling and ensemble learning strategies embedded in the self-supervised framework. We first propose a location-based sampling strategy to integrate the complementary advantages of semantic and spatial characteristics. Whereafter, a Siamese network with momentum update is introduced to generate representative vectors, which are used to optimize the feature extractor. Finally, we particularly embed global contrastive and local location tasks in the framework, which aims to leverage the complementarity between the high-level semantic features and low-level texture features. Such complementarity is significant for mitigating the feature-specificity and improving the generalizability, thus effectively improving the performance of downstream tasks. Extensive experiments on representative benchmark datasets demonstrate that GLNet performs favorably against the state-of-the-art SSL methods. Specifically, GLNet improves MoCo-v3 by 2.4% accuracy on ImageNet dataset, while improves 2% accuracy and consumes only 75% training time on the ImageNet-100 dataset. In addition, GLNet is appealing in its compatibility with popular SSL frameworks. Code is available at GLNet.

Currently, most existing methods using hyperspectral image to assist seed identification only consider the spectral information but ignore the spatial information resulting in unsatisfactory classification results. To cope with this issue, we propose a spatial, spectral, and texture-aware attention network to identify corn varieties, called SSTNet. Specifically, we first employ 3D convolution to extract the spatial and inter-spectral features. Subsequently, we utilize 2D convolution to extract the spatial and texture features. Meanwhile, we embed an attention mechanism into the 2D convolution module to further refine the spatial and texture features. The advantageous complementary properties of 3D and 2D convolutions allow the spatial and textural features of hyperspectral images to be fully exploited. Besides, we construct a hyperspectral image dataset including 1200 samples of 10 corn varieties. Experiments on our proposed dataset demonstrate that our SSTNet outperforms the state-of-the-art methods for identifying corn varieties.

Recently, image restoration has attracted considerable attention from researchers, and these methods generally restore degraded images based on the atmospheric scattering model (ATSM) and retinex model (RM). The two models only take into the single attenuation process during imaging, thereby introducing undesirable results. To deal with this issue, we propose an image restoration method based on a generalized image formation model (GIFM). First, unlike the existing image restoration methods, we rebuild a novel image formation model, which describes the light attenuation process that includes the light source-scene path and scene-sensor path. Second, we construct an objective optimization function to decompose a degraded image into a color distorted component and color corrected component, and an augmented Lagrange multiplier-based alternating direction minimization algorithm is provided to solve the optimization problem. Finally, we fully consider the advantages of the small-scale neighborhood and large-scale neighborhood in image restoration, and an image itself brightness-based weighted fusion strategy is proposed to balance brightness enhancement and contrast improvement. Extensive experiments on three image enhancement datasets show that our GIFM achieves better results than state-of-the-art methods. Experiments further suggest that our GIFM performs well for image restoration of extreme scenes, keypoint detection, object detection, and image segmentation.

Underwater images typically suffer from color deviations and low visibility due to the wavelength-dependent light absorption and scattering. To deal with these degradation issues, we propose an efficient and robust underwater image enhancement method, called MLLE. Specifically, we first locally adjust the color and details of an input image according to a minimum color loss principle and a maximum attenuation map-guided fusion strategy. Afterward, we employ the integral and squared integral maps to compute the mean and variance of local image blocks, which are used to adaptively adjust the contrast of the input image. Meanwhile, a color balance strategy is introduced to balance the color differences between channel a and channel b in the CIELAB color space. Our enhanced results are characterized by vivid color, improved contrast, and enhanced details. Extensive experiments on three underwater image enhancement datasets demonstrate that our method outperforms the state-of-the-art methods. Our method is also appealing in its fast processing speed within 1s for processing an image of size 1024×1024×3 on a single CPU. Experiments further suggest that our method can effectively improve the performance of underwater image segmentation, keypoint detection, and saliency detection. The project page is available at https://li-chongyi.github.io/proj_MMLE.html.