Change detection is a basic task of remote sensing image processing. The research objective is to identify the change information of interest and filter out the irrelevant change information as interference factors. Recently, the rise in deep learning has provided new tools for change detection, which have yielded impressive results. However, the available methods focus mainly on the difference information between multitemporal remote sensing images and lack robustness to pseudochange information. To overcome the lack of resistance in current methods to pseudochanges, in this article, we propose a new method, namely, dual attentive fully convolutional Siamese networks, for change detection in high-resolution images. Through the dual attention mechanism, long-range dependencies are captured to obtain more discriminant feature representations to enhance the recognition performance of the model. Moreover, the imbalanced sample is a serious problem in change detection, i.e., unchanged samples are much more abundant than changed samples, which is one of the main reasons for pseudochanges. We propose the weighted double-margin contrastive loss to address this problem by punishing attention to unchanged feature pairs and increasing attention to changed feature pairs. The experimental results of our method on the change detection dataset and the building change detection dataset demonstrate that compared with other baseline methods, the proposed method realizes maximum improvements of 2.9% and 4.2%, respectively, in the F1 score. Our PyTorch implementation is available at https://github.com/lehaifeng/DASNet.

No abstract

No abstract

Hydrogels prepared from natural polymers have captured extensive attention over the past decades because of their exceptional biocompatibility and nontoxicity, ease of gelation, and functionalization. Thus, natural polymer hydrogels are considered as promising biomaterials that show great potential in the biomedical field. In drug-delivery systems, the extent and the rate with which the drugs reach their targets are highly carrierdependent, so the demand for intelligent drug-delivery systems is gradually increasing. Recently, natural polymer hydrogels functionalized with magnetic materials have been used as a novel smart response device for drug delivery because of the quick response and remote controllability. This review aims to give the latest advances of magnetic hydrogels based on natural polymers such as polysaccharide, protein, and DNA in drug-delivery systems. Specifically, the first part compares several general synthesis strategies of magnetic natural polymer hydrogels. The applications of magnetic natural polymer hydrogels are described in the second part. For the last part, an overview of the application in drug delivery for the magnetic hydrogels constructed from several representative natural polymers is presented.

A total of 1050 juvenile Jian carp (Cyprinus carpio var. Jian) (8.20 ± 0.02 g) were fed diets containing seven graded levels of thiamin (0.25, 0.48, 0.79, 1.06, 1.37, 1.63 and 2.65 mg kg−1) for 60 days to investigate the effects of thiamin on growth, body composition and digestive enzyme activities. Percent weight gain (PWG), feed intake and feed efficiency (FE) were the lowest in fish fed the basal diet (P < 0.05). Protein productive value and lipid productive value increased with increasing dietary thiamin levels up to 1.06 and 0.79 mg kg−1 diet, respectively (P < 0.05). Body protein and lipid increased with increasing dietary thiamin levels (P < 0.05), while moisture and ash of fish carcasses decreased with the increase in dietary thiamin supplementation (P < 0.05). Intestinal folds height had a similar trend to PWG (P < 0.05). Activities of α‐amylase, lipase, trypsin, Na+, K+‐ATPase, alkaline phosphatase and gamma‐glutamyl transpeptidase in intestine were all affected by the dietary thiamin (P < 0.05). In conclusion, thiamin could improve growth and intestinal enzyme activities of juvenile Jian carp. The dietary thiamin requirement of juvenile Jian carp (8.0–60.2 g) based on PWG was 1.02 mg kg−1 diet.