Image-level Weakly Supervised Semantic Segmentation (WSSS) has garnered significant attention due to its low annotation costs. Current single-stage state-of-the-art WSSS methods mainly rely on Vision Transformer (ViT) to extract features from input images, generating more complete segmentation results based on comprehensive semantic information. However, these ViT-based methods often suffer from over-smoothing issues in segmentation results. In this paper, we identify that attenuated high-frequency features mislead the decoder of ViT-based WSSS models, resulting in over-smoothed false segmentation. To address this, we propose a Frequency Feature Rectification (FFR) framework to rectify the false segmentations caused by attenuated high-frequency features and enhance the learning of high-frequency features in the decoder. Quantitative and qualitative experimental results demonstrate that our FFR framework can effectively address the attenuated high-frequency caused over-smoothed segmentation issue and achieve new state-of-the-art WSSS performances. Codes are available at https://github.com/yay97/FFR.

Image-level Weakly Supervised Semantic Segmentation (WSSS) has received increasing attention due to its low an-notation cost. Class Activation Mapping (CAM) generated through classifier weights in WSSS inevitably ignores cer-tain useful cues, while the CAM generated through class prototypes can alleviate that. However, because of the dif-ferent goals of image classification and semantic segmentation, the class prototypes still focus on activating primary discriminative pixels learned from classification loss, leading to incomplete CAM. In this paper, we propose a plug-and-play Prototype-based Secondary Discriminative Pixels Mining (PSDPM) framework for enabling class prototypes to activate more secondary discriminative pixels, thus gen-erating a more complete CAM. Specifically, we introduce a Foreground Pixel Estimation Module (FPEM) for esti-mating potential foreground pixels based on the correlations between primary and secondary discriminative pix-els and the semantic segmentation results of baseline meth-ods. Then, we enable WSSS model to learn discriminative features from secondary discriminative pixels through a consistency loss calculated between FPEM result and class-prototype CAM. Experimental results show that our PSDPM improves various baseline methods significantly and achieves new state-of-the-art performances on WSSS benchmarks. Codes are available at https://github.com/xinqiaozhao/PSDPM.

This study aimed to identify and assess vegetation indices (VIs) and their optimal band combinations using unmanned aerial vehicle (UAV) hyperspectral imagery for the quantitative inversion of wheat stripe rust. This would offer guidance for selecting rust-resistant phenotypes and facilitate large-scale disease monitoring using aerial and spaceborne remote sensing images. The experimental design encompassed 960 wheat varieties (strains) in agricultural fields. Hyperspectral imagery was acquired at 100m altitude during different disease stages, and disease index (DI) was investigated per plot. A custom program explored VIs with two, three, and four bands using 30 calculation methods and 3,463,790 band combinations. Regression models employed three-fold cross-validation and multilayer perceptron (MLP) algorithms, with the mean R2value indicating optimal index and band combinations. The results revealed that the chosen VIs were effective in inverting the DI. Selected two-band VIs included MGRVI (531, 571), with R2=0.746±0.01618; the optimal three-band VIs was ARI2 (531, 550±10, 640±25), with R2=0.755±0.00896; and the best four-band VIs was DBSI (531, 551, 750, 799), with R2=0.778±0.01300, which was comparable to full-band modeling (R2=0.775±0.01508). The models’ performance improved with an increasing number of bands in the VIs. This study demonstrated that appropriate multi-VIs modeling enhances performance compared to single-VIs modeling, e.g., six combinations of VIs achieved R2=0.790±0.01141. These findings underscore the potential of integrating machine learning algorithms and vegetation indices for quantifying wheat rust diseases, laying the foundation for developing airborne and spaceborne imaging sensors for large-scale wheat rust monitoring.

Phytoplankton carbon, an important biogeochemical and ecological parameter, plays a critical role in the carbon cycle and in global warming reduction. Estimation of phytoplankton carbon in inland waters on a large scale using remote sensing is useful for understanding, evaluating, and monitoring the carbon dynamics, and, in particular, for determining the spatial–temporal variation of primary production in inland waters. In a correlation analysis of the phytoplankton carbon concentration and water components, the result revealed no significant correlation between the chlorophyll-a concentration and phytoplankton carbon concentration in inland waters. However, the absorption peak height of particles at 675 nm, which is defined as the absorption at 675 nm subtracted by that at 660 nm, was found to be closely correlated with the phytoplankton carbon concentration. Thus, the absorption peak height of particles at 675 nm could be used as an indicator of the phytoplankton carbon concentration. A semianalytical method based on the remote-sensing reflectance in Sentinel-3 Ocean and Land Color Instrument (OLCI) bands 8, 9, and 17 was developed to derive the absorption peak of particles at a wavelength of 675 nm. Finally, an algorithm for estimating the phytoplankton carbon concentration in inland waters using OLCI bands 8, 9, and 17 was constructed. From 2013 to 2018, eight field campaigns were conducted in inland lakes in different seasons, and the optical properties, optically active water components, and phytoplankton carbon concentrations were obtained. An assessment of its accuracy using an independent data set demonstrated that the algorithm performance is acceptable (mean absolute percentage error, 48.6%, and root mean square error, 0.36 mg/L). As a demonstration, the algorithm was successfully applied to map the phytoplankton carbon concentration in Taihu Lake and Chaohu Lake, China, using OLCI images acquired on December 5, 2017, and August 5, 2018 and December 8, 2017, and August 7, 2017, and the spatial variation of the phytoplankton carbon concentration in Taihu Lake and Chaohu Lake was thoroughly examined. A semianalytical remote-sensing method, instead of a traditional time-consuming approach, was developed in this article, which can be used to estimate phytoplankton carbon concentration quickly, and provides an effective way to map the phytoplankton carbon concentration in inland water on a large scale.