Search

Most of the recent image segmentation methods have tried to achieve the utmost segmentation results using large-scale pixel-level annotated data sets. However, obtaining these pixel-level annotated training data is usually tedious and expensive. In this work, we address the task of semisupervised semantic segmentation, which reduces the need for large numbers of pixel-level annotated images. We propose a method for semisupervised semantic segmentation by improving the confidence of the predicted class probability map via two parts. First, we build an adversarial framework that regards the segmentation network as the generator and uses a fully convolutional network as the discriminator. The adversarial learning makes the prediction class probability closer to 1. Second, the information entropy of the predicted class probability map is computed to represent the unpredictability of the segmentation prediction. Then, we infer the label-error map of the segmentation prediction and minimize the uncertainty on misclassified regions for unlabeled images. In contrast to existing semisupervised and weakly supervised semantic segmentation methods, the proposed method results in more confident predictions by focusing on the misclassified regions, especially the boundary regions. Our experimental results on the PASCAL VOC 2012 and PASCAL-CONTEXT data sets show that the proposed method achieves competitive segmentation performance.

Light plays an important role in determining plant architecture, which greatly influences crop yield. However, the precise mechanisms by which light signaling regulates bud outgrowth remain to be identified. Here, we show that light regulates bud outgrowth via both HY5 and brassinosteroid (BR)-dependent pathways in tomato. Inactivation of the red-light photoreceptor PHYB, or deficiencies in PHYB or the blue-light photoreceptor CRY1a, inhibits bud outgrowth and leads to decreased accumulation of HY5 protein and increased transcript level of BRANCHED1 ( BRC1 ), a central integrator of branching signals. HY5, functioning as a mobile systemic signal from leaves, promotes bud outgrowth by directly suppressing BRC1 transcript and activating the transcript of BR biosynthesis genes within the lateral buds in tomato. Furthermore, BRC1 prevents the accumulation of cytokinin (CK) and gibberellin (GA) by directly inhibiting the transcript of CK synthesis gene LOG4 , while increasing the transcript levels of CK and GA degradation genes ( CKX7 , GA2ox4 , and GA2ox5 ), leading to an arrest of bud outgrowth. Moreover, bud outgrowth occurs predominantly in the day due to the suppression of BRC1 transcript by HY5. These findings demonstrate that light-inducible HY5 acts as a systemic signaling factor in fine-tuning the bud outgrowth of tomato.

Phytosulfokine (PSK) is a danger-associated molecular pattern recognized by PHYTOSULFOKINE RECEPTOR 1 (PSKR1) and initiates intercellular signaling to coordinate different physiological processes, especially in the defense response to the necrotrophic fungus Botrytis cinerea. The activity of peptide receptors is largely influenced by different posttranslational modifications, which determine intercellular peptide signal outputs. To date, the posttranslational modification to PHYTOSULFOKINE RECEPTOR 1 (PSKR1) remains largely unknown. Here, we show that tomato (Solanum lycopersicum) PSKR1 is regulated by the ubiquitin/proteasome degradation pathway. Using multiple protein–protein interactions and ubiquitylation analyses, we identified that plant U-box E3 ligases PUB12 and PUB13 interacted with PSKR1, among which PUB13 caused PSKR1 ubiquitylation at Lys-748 and Lys-905 sites to control PSKR1 abundance. However, this posttranslational modification was attenuated upon addition of PSK. Moreover, the disease symptoms observed in PUB13 knock-down and overexpression lines demonstrated that PUB13 significantly suppressed the PSK-initiated defense response. This highlights an important regulatory function for the turnover of a peptide receptor by E3 ligase-mediated ubiquitylation in the plant defense response.

Most existing studies performed video denoising by using multiple adjacent noisy frames to recover one clean frame; however, despite achieving relatively good quality for each individual frame, these approaches may result in visual flickering when the denoised frames are considered in sequence. In this paper, instead of separately restoring each clean frame, we propose a multiframe-to-multiframe (MM) denoising scheme that simultaneously recovers multiple clean frames from consecutive noisy frames. The proposed MM denoising scheme uses a training strategy that optimizes the denoised video from both the spatial and temporal dimensions, enabling better temporal consistency in the denoised video. Furthermore, we present an MM network (MMNet), which adopts a spatiotemporal convolutional architecture that considers both the interframe similarity and single-frame characteristics. Benefiting from the underlying parallel mechanism of the MM denoising scheme, MMNet achieves a highly competitive denoising efficiency. Extensive analyses and experiments demonstrate that MMNet outperforms the state-of-the-art video denoising methods, yielding temporal consistency improvements of at least 13.3% and running more than 2 times faster than the other methods.

Herbivory severely affects plant growth, posing a threat to crop production. Calcium ion (Ca

Fruits are excellent sources of essential vitamins and health-boosting minerals. Recently, regulation of fruit ripening by both internal and external cues for the improvement of fruit quality and shelf life has received considerable attention. Rosmarinic acid (RA) is a kind of natural plant-derived polyphenol, widely used in the drug therapy and food industry due to its distinct physiological functions. However, the role of RA in plant growth and development, especially at the postharvest period of fruits, remains largely unknown. Here, we demonstrated that postharvest RA treatment delayed the ripening in tomato fruits. Exogenous application of RA decreased ripening-associated ethylene production and inhibited the fruit color change from green to red based on the decline in lycopene accumulation. We also found that the degradation of sucrose and malic acid during ripening was significantly suppressed in RA-treated tomato fruits. The results of metabolite profiling showed that RA application promoted the accumulation of multiple amino acids in tomato fruits, such as aspartic acid, serine, tyrosine, and proline. Meanwhile, RA application also strengthened the antioxidant system by increasing both the activity of antioxidant enzymes and the contents of reduced forms of antioxidants. These findings not only unveiled a novel function of RA in fruit ripening, but also indicated an attractive strategy to manage and improve shelf life, flavor, and sensory evolution of tomato fruits.