Hasil untuk "Maps"

Julius Adebayo, J. Gilmer, Michael Muelly et al.

Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work, we propose an actionable methodology to evaluate what kinds of explanations a given method can and cannot provide. We find that reliance, solely, on visual assessment can be misleading. Through extensive experiments we show that some existing saliency methods are independent both of the model and of the data generating process. Consequently, methods that fail the proposed tests are inadequate for tasks that are sensitive to either data or model, such as, finding outliers in the data, explaining the relationship between inputs and outputs that the model learned, and debugging the model. We interpret our findings through an analogy with edge detection in images, a technique that requires neither training data nor model. Theory in the case of a linear model and a single-layer convolutional neural network supports our experimental findings.

T. Croll

ISOLDE is an interactive molecular-dynamics environment for rebuilding models against experimental cryo-EM or crystallographic maps. Analysis of its results reinforces the need for great care when validating models built into low-resolution data.

Deng-Ping Fan, Ming-Ming Cheng, Yun Liu et al.

Foreground map evaluation is crucial for gauging the progress of object segmentation algorithms, in particular in the field of salient object detection where the purpose is to accurately detect and segment the most salient object in a scene. Several measures (e.g., area-under-the-curve, F1-measure, average precision, etc.) have been used to evaluate the similarity between a foreground map and a ground-truth map. The existing measures are based on pixel-wise errors and often ignore the structural similarities. Behavioral vision studies, however, have shown that the human visual system is highly sensitive to structures in scenes. Here, we propose a novel, efficient (0.005 s per image), and easy to calculate measure known as S-measure (structural measure) to evaluate foreground maps. Our new measure simultaneously evaluates region-aware and object-aware structural similarity between a foreground map and a ground-truth map. We demonstrate superiority of our measure over existing ones using 4 meta-measures on 5 widely-used benchmark datasets. Furthermore, we conduct a behavioral judgment study over a new database. Data from 45 subjects shows that on average they preferred the saliency maps chosen by our measure over the saliency maps chosen by the state-of-the-art measures. Our experimental results offer new insights into foreground map evaluation where current measures fail to truly examine the strengths and weaknesses of models. Code: https://github.com/DengPingFan/S-measure.

Neva C. Durand, James T. Robinson, M. Shamim et al.

Hi-C experiments study how genomes fold in 3D, generating contact maps containing features as small as 20 bp and as large as 200 Mb. Here we introduce Juicebox, a tool for exploring Hi-C and other contact map data. Juicebox allows users to zoom in and out of Hi-C maps interactively, just as a user of Google Earth might zoom in and out of a geographic map. Maps can be compared to one another, or to 1D tracks or 2D feature sets.

Feng Tian, Dechang Yang, Yuqi Meng et al.

Abstract With the goal of charting plant transcriptional regulatory maps (i.e. transcription factors (TFs), cis-elements and interactions between them), we have upgraded the TF-centred database PlantTFDB (http://planttfdb.cbi.pku.edu.cn/) to a plant regulatory data and analysis platform PlantRegMap (http://plantregmap.cbi.pku.edu.cn/) over the past three years. In this version, we updated the annotations for the previously collected TFs and set up a new section, ‘extended TF repertoires’ (TFext), to allow users prompt access to the TF repertoires of newly sequenced species. In addition to our regular TF updates, we are dedicated to updating the data on cis-elements and functional interactions between TFs and cis-elements. We established genome-wide conservation landscapes for 63 representative plants and then developed an algorithm, FunTFBS, to screen for functional regulatory elements and interactions by coupling the base-varied binding affinities of TFs with the evolutionary footprints on their binding sites. Using the FunTFBS algorithm and the conservation landscapes, we further identified over 20 million functional TF binding sites (TFBSs) and two million functional interactions for 21 346 TFs, charting the functional regulatory maps of these 63 plants. These resources are publicly available at PlantRegMap (http://plantregmap.cbi.pku.edu.cn/) and a cloud-based mirror (http://plantregmap.gao-lab.org/), providing the plant research community with valuable resources for decoding plant transcriptional regulatory systems.

Peng-Tao Jiang, Chang-Bin Zhang, Qibin Hou et al.

The class activation maps are generated from the final convolutional layer of CNN. They can highlight discriminative object regions for the class of interest. These discovered object regions have been widely used for weakly-supervised tasks. However, due to the small spatial resolution of the final convolutional layer, such class activation maps often locate coarse regions of the target objects, limiting the performance of weakly-supervised tasks that need pixel-accurate object locations. Thus, we aim to generate more fine-grained object localization information from the class activation maps to locate the target objects more accurately. In this paper, by rethinking the relationships between the feature maps and their corresponding gradients, we propose a simple yet effective method, called LayerCAM. It can produce reliable class activation maps for different layers of CNN. This property enables us to collect object localization information from coarse (rough spatial localization) to fine (precise fine-grained details) levels. We further integrate them into a high-quality class activation map, where the object-related pixels can be better highlighted. To evaluate the quality of the class activation maps produced by LayerCAM, we apply them to weakly-supervised object localization and semantic segmentation. Experiments demonstrate that the class activation maps generated by our method are more effective and reliable than those by the existing attention methods. The code will be made publicly available.

C. Bennett, D. Larson, J. Weiland et al.

We present the final nine-year maps and basic results from the Wilkinson Microwave Anisotropy Probe (WMAP) mission. The full nine-year analysis of the time-ordered data provides updated characterizations and calibrations of the experiment. We also provide new nine-year full sky temperature maps that were processed to reduce the asymmetry of the effective beams. Temperature and polarization sky maps are examined to separate cosmic microwave background (CMB) anisotropy from foreground emission, and both types of signals are analyzed in detail. We provide new point source catalogs as well as new diffuse and point source foreground masks. An updated template-removal process is used for cosmological analysis; new foreground fits are performed, and new foreground-reduced CMB maps are presented. We now implement an optimal C−1 weighting to compute the temperature angular power spectrum. The WMAP mission has resulted in a highly constrained ΛCDM cosmological model with precise and accurate parameters in agreement with a host of other cosmological measurements. When WMAP data are combined with finer scale CMB, baryon acoustic oscillation, and Hubble constant measurements, we find that big bang nucleosynthesis is well supported and there is no compelling evidence for a non-standard number of neutrino species (Neff = 3.84 ± 0.40). The model fit also implies that the age of the universe is t0 = 13.772 ± 0.059 Gyr, and the fit Hubble constant is H0 = 69.32 ± 0.80 km s−1 Mpc−1. Inflation is also supported: the fluctuations are adiabatic, with Gaussian random phases; the detection of a deviation of the scalar spectral index from unity, reported earlier by the WMAP team, now has high statistical significance (ns = 0.9608 ± 0.0080); and the universe is close to flat/Euclidean (). Overall, the WMAP mission has resulted in a reduction of the cosmological parameter volume by a factor of 68,000 for the standard six-parameter ΛCDM model, based on CMB data alone. For a model including tensors, the allowed seven-parameter volume has been reduced by a factor 117,000. Other cosmological observations are in accord with the CMB predictions, and the combined data reduces the cosmological parameter volume even further. With no significant anomalies and an adequate goodness of fit, the inflationary flat ΛCDM model and its precise and accurate parameters rooted in WMAP data stands as the standard model of cosmology.

G. Yen

Nikola B. Kovachki, Zong-Yi Li, Burigede Liu et al.

The classical development of neural networks has primarily focused on learning mappings between finite dimensional Euclidean spaces or finite sets. We propose a generalization of neural networks to learn operators, termed neural operators, that map between infinite dimensional function spaces. We formulate the neural operator as a composition of linear integral operators and nonlinear activation functions. We prove a universal approximation theorem for our proposed neural operator, showing that it can approximate any given nonlinear continuous operator. The proposed neural operators are also discretization-invariant, i.e., they share the same model parameters among different discretization of the underlying function spaces. Furthermore, we introduce four classes of efficient parameterization, viz., graph neural operators, multi-pole graph neural operators, low-rank neural operators, and Fourier neural operators. An important application for neural operators is learning surrogate maps for the solution operators of partial differential equations (PDEs). We consider standard PDEs such as the Burgers, Darcy subsurface flow, and the Navier-Stokes equations, and show that the proposed neural operators have superior performance compared to existing machine learning based methodologies, while being several orders of magnitude faster than conventional PDE solvers.

Chen Huang, Oier Mees, Andy Zeng et al.

Grounding language to the visual observations of a navigating agent can be performed using off-the-shelf visual-language models pretrained on Internet-scale data (e.g., image captions). While this is useful for matching images to natural language descriptions of object goals, it remains disjoint from the process of mapping the environment, so that it lacks the spatial precision of classic geometric maps. To address this problem, we propose VLMaps, a spatial map representation that directly fuses pretrained visual-language features with a 3D reconstruction of the physical world. VLMaps can be autonomously built from video feed on robots using standard exploration approaches and enables natural language indexing of the map without additional labeled data. Specifically, when combined with large language models (LLMs), VLMaps can be used to (i) translate natural language commands into a sequence of open-vocabulary navigation goals (which, beyond prior work, can be spatial by construction, e.g., “in between the sofa and the TV” or “three meters to the right of the chair”) directly localized in the map, and (ii) can be shared among multiple robots with different embodiments to generate new obstacle maps on-the-fly (by using a list of obstacle categories). Extensive experiments carried out in simulated and real-world environments show that VLMaps enable navigation according to more complex language instructions than existing methods. Videos are available at https://vlmaps.github.io.

Li An, Hongbo M. Xie, M. H. Chin et al.

BackgroundGene expression signatures in the mammalian brain hold the key to understanding neural development and neurological disease. Researchers have previously used voxelation in combination with microarrays for acquisition of genome-wide atlases of expression patterns in the mouse brain. On the other hand, some work has been performed on studying gene functions, without taking into account the location information of a gene's expression in a mouse brain. In this paper, we present an approach for identifying the relation between gene expression maps obtained by voxelation and gene functions.ResultsTo analyze the dataset, we chose typical genes as queries and aimed at discovering similar gene groups. Gene similarity was determined by using the wavelet features extracted from the left and right hemispheres averaged gene expression maps, and by the Euclidean distance between each pair of feature vectors. We also performed a multiple clustering approach on the gene expression maps, combined with hierarchical clustering. Among each group of similar genes and clusters, the gene function similarity was measured by calculating the average gene function distances in the gene ontology structure.By applying our methodology to find similar genes to certain target genes we were able to improve our understanding of gene expression patterns and gene functions.By applying the clustering analysis method, we obtained significant clusters, which have both very similar gene expression maps and very similar gene functions respectively to their corresponding gene ontologies. The cellular component ontology resulted in prominent clusters expressed in cortex and corpus callosum. The molecular function ontology gave prominent clusters in cortex, corpus callosum and hypothalamus. The biological process ontology resulted in clusters in cortex, hypothalamus and choroid plexus. Clusters from all three ontologies combined were most prominently expressed in cortex and corpus callosum.ConclusionThe experimental results confirm the hypothesis that genes with similar gene expression maps might have similar gene functions. The voxelation data takes into account the location information of gene expression level in mouse brain, which is novel in related research. The proposed approach can potentially be used to predict gene functions and provide helpful suggestions to biologists.

M. Haklay, Patrick Weber

The OpenStreetMap project is a knowledge collective that provides user-generated street maps. OSM follows the peer production model that created Wikipedia; its aim is to create a set of map data that's free to use, editable, and licensed under new copyright schemes. A considerable number of contributors edit the world map collaboratively using the OSM technical infrastructure, and a core group, estimated at approximately 40 volunteers, dedicate their time to creating and improving OSM's infrastructure, including maintaining the server, writing the core software that handles the transactions with the server, and creating cartographical outputs. There's also a growing community of software developers who develop software tools to make OSM data available for further use across different application domains, software platforms, and hardware devices. The OSM project's hub is the main OSM Web site.

B. Hoskins, M. McIntyre, A. Robertson

D. Kahneman

B. Kosko

E. Tolman

R. Coifman, Stéphane Lafon

J. Ooijen, J. Ooijen, JW van 't Verlaat et al.

R. Markello, J. Hansen, Zhen-Qi Liu et al.

Imaging technologies are increasingly used to generate high-resolution reference maps of brain structure and function. Comparing experimentally generated maps to these reference maps facilitates cross-disciplinary scientific discovery. Although recent data sharing initiatives increase the accessibility of brain maps, data are often shared in disparate coordinate systems, precluding systematic and accurate comparisons. Here we introduce neuromaps, a toolbox for accessing, transforming and analyzing structural and functional brain annotations. We implement functionalities for generating high-quality transformations between four standard coordinate systems. The toolbox includes curated reference maps and biological ontologies of the human brain, such as molecular, microstructural, electrophysiological, developmental and functional ontologies. Robust quantitative assessment of map-to-map similarity is enabled via a suite of spatial autocorrelation-preserving null models. neuromaps combines open-access data with transparent functionality for standardizing and comparing brain maps, providing a systematic workflow for comprehensive structural and functional annotation enrichment analysis of the human brain. neuromaps is a toolbox for accessing, transforming and comparing human neuroimaging data.

J. Burt, Markus Helmer, Maxwell Shinn et al.

Studies of large-scale brain organization have revealed interesting relationships between spatial gradients in brain maps across multiple modalities. Evaluating the significance of these findings requires establishing statistical expectations under a null hypothesis of interest. Through generative modeling of synthetic data that instantiate a specific null hypothesis, quantitative benchmarks can be derived for arbitrarily complex statistical measures. Here, we present a generative null model, provided as an open-access software platform, that generates surrogate maps with spatial autocorrelation (SA) matched to SA of a target brain map. SA is a prominent and ubiquitous property of brain maps that violates assumptions of independence in conventional statistical tests. Our method can simulate surrogate brain maps, constrained by empirical data, that preserve the SA of cortical, subcortical, parcellated, and dense brain maps. We characterize how SA impacts p-values in pairwise brain map comparisons. Furthermore, we demonstrate how SA-preserving surrogate maps can be used in gene ontology enrichment analyses to test hypotheses of interest related to brain map topography. Our findings demonstrate the utility of SA-preserving surrogate maps for hypothesis testing in complex statistical analyses, and underscore the need to disambiguate meaningful relationships from chance associations in studies of large-scale brain organization.