Species distribution modeling (SDM) is widely used in ecology and conservation. Currently, the most available data for SDM are species presence‐only records (available through digital databases). ...There have been many studies comparing the performance of alternative algorithms for modeling presence‐only data. Among these, a 2006 paper from Elith and colleagues has been particularly influential in the field, partly because they used several novel methods (at the time) on a global data set that included independent presence–absence records for model evaluation. Since its publication, some of the algorithms have been further developed and new ones have emerged. In this paper, we explore patterns in predictive performance across methods, by reanalyzing the same data set (225 species from six different regions) using updated modeling knowledge and practices. We apply well‐established methods such as generalized additive models and MaxEnt, alongside others that have received attention more recently, including regularized regressions, point‐process weighted regressions, random forests, XGBoost, support vector machines, and the ensemble modeling framework biomod. All the methods we use include background samples (a sample of environments in the landscape) for model fitting. We explore impacts of using weights on the presence and background points in model fitting. We introduce new ways of evaluating models fitted to these data, using the area under the precision‐recall gain curve, and focusing on the rank of results. We find that the way models are fitted matters. The top method was an ensemble of tuned individual models. In contrast, ensembles built using the biomod framework with default parameters performed no better than single moderate performing models. Similarly, the second top performing method was a random forest parameterized to deal with many background samples (contrasted to relatively few presence records), which substantially outperformed other random forest implementations. We find that, in general, nonparametric techniques with the capability of controlling for model complexity outperformed traditional regression methods, with MaxEnt and boosted regression trees still among the top performing models. All the data and code with working examples are provided to make this study fully reproducible.
Real-time semantic segmentation has attracted wide attention in the computer vision field, and its performance depends on both rich semantic information and high-resolution information. Most networks ...fastly reduce image resolution or prune feature channels in the coding stage to improve the computing speed and concatenate the shallow feature to the deep feature in the decoding stage for filling in the high-resolution details. Here, we propose a new real-time semantic image segmentation method called guided down-sampling network. The guided down-sampling decomposes the original image into a group of compressed images that replace the original image as the input of the encoding layers. This operation reduces the size of the feature map and meanwhile retains the most spatial information of the original image. Furthermore, a two-branch sub-network is designed to extract semantic information and restore high-resolution image details from compressed images for better supervising feature learning. Our network is tested on the Cityscapes dataset on a single Nvidia GeForce GTX 1080Ti GPU, and the competitive results of 113 FPS and 75.6% mIoU have been achieved. The code is available at ( https://github.com/ldrunning/segmentation).
•MRIformer is designed based on the characteristics of wind speed data.•ASI block is used to realize subsequence information mining and interaction.•MRI block is used to realize multi-resolution data ...mining and information fusion.•The proposed model is compared with twelve mainstream prediction models.
Wind speed prediction is crucial for managing energy consumption in wind farms. Traditional wind speed prediction techniques often overlook two essential characteristics of wind speed data: (a) the downsampled wind speed data can retain cyclic and trend information, which is valuable for the model. (b) Multi-resolution speed data exhibited distinct patterns, enabling the model to extract insights from various perspectives. Considering the above two characteristics, this paper presents a novel approach called the Multi-Resolution Interactive transformer (MRIformer), which consists of the ASI block and the MRI block. The ASI block utilizes two different attention mechanisms to extract temporal information and enhance interactive learning among subsequences while downsampling wind speed data. The MRI block utilizes a tree structure to stack multiple layers of ASI blocks, enabling the analysis of wind speed data at various resolutions. By incorporating residual connections and multi-head attention, the MRI block effectively fuses data with different resolutions. Comparative experiments on three real-world datasets led to the following conclusions. (a) MRIformer exceeded 14 state-of-the-art baselines on all datasets and achieved a performance improvement of over 7.5%. (b) The effectiveness of the designed structure is demonstrated through component replacement and ablation experiments.
Abstract
Resource constraints often force researchers to downsize the list of tokens returned by a corpus query. This paper sketches a methodology for down-sampling and offers a survey of current ...practices. We build on earlier work and extend the evaluation of down-sampling designs to settings where tokens are clustered by text file and lexeme. Our case study deals with third-person present-tense verb inflection in Early Modern English and focuses on five predictors: year, gender, genre, frequency, and phonological context. We evaluate two strategies for selecting 2,000 (out of 11,645) tokens: simple down-sampling, where each hit has the same selection probability; and structured down-sampling, where this probability is inversely proportional to the author- and verb-specific token count. We form 500 subsamples using each scheme and compare regression results to a reference model fit to the full set of cases. We observe that structured down-sampling shows better performance on several evaluation criteria.
We study the dual problem of image super-resolution (SR), which we term image compact-resolution (CR). Opposite to image SR that hallucinates a visually plausible high-resolution image given a ...low-resolution input, image CR provides a low-resolution version of a high-resolution image, such that the low-resolution version is both visually pleasing and as informative as possible compared to the high-resolution image. We propose a convolutional neural network (CNN) for image CR, namely, CNN-CR, inspired by the great success of CNN for image SR. Specifically, we translate the requirements of image CR into operable optimization targets for training CNN-CR: the visual quality of the compact resolved image is ensured by constraining its difference from a naively downsampled version and the information loss of image CR is measured by upsampling/super-resolving the compact-resolved image and comparing that to the original image. Accordingly, CNN-CR can be trained either separately or jointly with a CNN for image SR. We explore different training strategies as well as different network structures for CNN-CR. Our experimental results show that the proposed CNN-CR clearly outperforms simple bicubic downsampling and achieves on average 2.25 dB improvement in terms of the reconstruction quality on a large collection of natural images. We further investigate two applications of image CR, i.e., low-bit-rate image compression and image retargeting. Experimental results show that the proposed CNN-CR helps achieve significant bits saving than High Efficiency Video Coding when applied to image compression and produce visually pleasing results when applied to image retargeting.
The random forest (RF) algorithm is an ensemble of classification or regression trees and is widely used, including for species distribution modelling (SDM). Many researchers use implementations of ...RF in the R programming language with default parameters to analyse species presence‐only data together with ‘background' samples. However, there is good evidence that RF with default parameters does not perform well for such ‘presence‐background' modelling. This is often attributed to the disparity between the number of presence and background samples, also known as 'class imbalance', and several solutions have been proposed. Here, we first set the context: the background sample should be large enough to represent all environments in the region. We then aim to understand the drivers of poor performance of RF when models are fitted to presence‐only species data alongside background samples. We show that 'class overlap' (where both classes occur in the same environment) is an important driver of poor performance, alongside class imbalance. Class overlap can even degrade performance for presence–absence data. We explain, test and evaluate suggested solutions. Using simulated and real presence‐background data, we compare performance of default RF with other weighting and sampling approaches. Our results demonstrate clear evidence of improvement in the performance of RFs when techniques that explicitly manage imbalance are used. We show that these either limit or enforce tree depth. Without compromising the environmental representativeness of the sampled background, we identify approaches to fitting RF that ameliorate the effects of imbalance and overlap and allow excellent predictive performance. Understanding the problems of RF in presence‐background modelling allows new insights into how best to fit models, and should guide future efforts to best deal with such data.
Subpixel rendering approaches are necessary to provide apparently high resolution images when there are difficulties in implementing the display with the target high resolution. This paper presents a ...subpixel rendering technique based on the convolutional neural network (CNN) for a diamond-shaped PenTile pixel arrangement. The proposed subpixel rendering network (SPRNN) takes the concatenated input of high resolution image and pixel arrangement information for each color component. SPRNNs for three colors share weights, leading to the substantial reduction on the number of weights. The loss function is defined as the squared error between original and virtual images, where virtual images are generated from the down-sampled SPRNN outputs by the human visual system (HVS) model. The proposed SPRNN outperforms other down-sampling algorithms such as DPD, DSD, DDSD, PDAF, DSD-FA, DDSD-FA, and QPD in terms of PSNRz and SSIMz estimated from virtual images as well as SPA metrics measured at the down-sampled images. PSNRz and SSIMz of the proposed SPRNN are measured as 32.6027 dB and 0.9813. In addition, the light version SPRNN (SPRNNL) also achieves high PSNRz and SSIMz of 32.5192 dB and 0.9810 that are bigger than previous down-sampling schemes, while its computational complexity is reduced by around 99.8%, compared to SPRNN.
•The subpixel rendering network is proposed for a diamond-shaped PenTile layout.•The proposed neural network uses additional pixel arrangement information.•The proposed neural network outperforms previous down-sampling algorithms.•The total number of weights is reduced by weight sharing for all color components.
Though widely used in image classification, convolutional neural networks (CNNs) are prone to noise interruptions, i.e. the CNN output can be drastically changed by small image noise. To improve the ...noise robustness, we try to integrate CNNs with wavelet by replacing the common down-sampling (max-pooling, strided-convolution, and average pooling) with discrete wavelet transform (DWT). We firstly propose general DWT and inverse DWT (IDWT) layers applicable to various orthogonal and biorthogonal discrete wavelets like Haar, Daubechies, and Cohen, etc., and then design wavelet integrated CNNs (WaveCNets) by integrating DWT into the commonly used CNNs (VGG, ResNets, and DenseNet). During the down-sampling, WaveCNets apply DWT to decompose the feature maps into the low-frequency and high-frequency components. Containing the main information including the basic object structures, the low-frequency component is transmitted into the following layers to generate robust high-level features. The high-frequency components are dropped to remove most of the data noises. The experimental results show that WaveCNets achieve higher accuracy on ImageNet than various vanilla CNNs. We have also tested the performance of WaveCNets on the noisy version of ImageNet, ImageNet-C and six adversarial attacks, the results suggest that the proposed DWT/IDWT layers could provide better noise-robustness and adversarial robustness. When applying WaveCNets as backbones, the performance of object detectors (i.e., faster R-CNN and RetinaNet) on COCO detection dataset are consistently improved. We believe that suppression of aliasing effect, i.e. separation of low frequency and high frequency information, is the main advantages of our approach. The code of our DWT/IDWT layer and different WaveCNets are available at https://github.com/CVI-SZU/WaveCNet .
Inspired by the recent advances of image super-resolution using convolutional neural network (CNN), we propose a CNN-based block up-sampling scheme for intra frame coding. A block can be down-sampled ...before being compressed by normal intra coding, and then up-sampled to its original resolution. Different from previous studies on down/up-sampling-based coding, the up-sampling methods in our scheme have been designed by training CNN instead of hand-crafted. We explore a new CNN structure for up-sampling, which features deconvolution of feature maps, multi-scale fusion, and residue learning, making the network both compact and efficient. We also design different networks for the up-sampling of luma and chroma components, respectively, where the chroma up-sampling CNN utilizes the luma information to boost its performance. In addition, we design a two-stage up-sampling process, the first stage being within the block-by-block coding loop, and the second stage being performed on the entire frame, so as to refine block boundaries. We also empirically study how to set the coding parameters of down-sampled blocks for pursuing the frame-level rate-distortion optimization. Our proposed scheme is implemented into the high-efficiency video coding (HEVC) reference software, and a comprehensive set of experiments have been performed to evaluate our methods. Experimental results show that our scheme achieves significant bits saving compared with the HEVC anchor, especially at low bit rates, leading to on average 5.5% BD-rate reduction on common test sequences and on average 9.0% BD-rate reduction on ultrahigh definition test sequences.
Deep Convolutional Neural Networks (CNNs), such as Dense Convolutional Network (DenseNet), have achieved great success for image representation learning by capturing deep hierarchical features. ...However, most existing network architectures of simply stacking the convolutional layers fail to enable them to fully discover local and global feature information between layers. In this paper, we mainly investigate how to enhance the local and global feature learning abilities of DenseNet by fully exploiting the hierarchical features from all convolutional layers. Technically, we propose an effective convolutional deep model termed Dense Residual Network (DRN) for the task of optical character recognition. To define DRN, we propose a refined residual dense block (r-RDB) to retain the ability of local feature fusion and local residual learning of original RDB, which can reduce the computing efforts of inner layers at the same time. After fully capturing local residual dense features, we utilize the sum operation and several r-RDBs to construct a new block termed global dense block (GDB) by imitating the construction of dense blocks to adaptively learn global dense residual features in a holistic way. Finally, we use two convolutional layers to design a down-sampling block to reduce the global feature size and extract more informative deeper features. Extensive results show that our DRN can deliver enhanced results, compared with other related deep models.
PDF
