Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 15 of 15 for “"Spatial pooling"”.

  1. Spatial pooling strategies for image quality assessment

    Recent image quality assessment (IQA) metrics achieve high correlation with human perception of image quality. Naturally, it is of interest to produce even better results. One promising method is to weight image quality measurements by visual importance. To this end, we describe three strategies - …

    texas Repository record for Spatial pooling strategies for image quality assessment (opens in a new tab)

  2. NEURAL ARCHITECTURE DESIGN AND APPLICATIONS

    … By replacing the attention module with a simple spatial pooling operator, we create PoolFormer, which achieves competitive performance across vision tasks. This supports our hypothesis that the general Transformer architecture, dubbed MetaFormer, is essential for model performance. MetaFormer …

    nus Repository record for NEURAL ARCHITECTURE DESIGN AND APPLICATIONS (opens in a new tab) Download file for NEURAL ARCHITECTURE DESIGN AND APPLICATIONS (opens in a new tab)

  3. Learning Along the Edge of Deep Neural Networks

    … by examining the convolutional, activation, and pooling layers, and showing a parallelism between this structure and another well-studied problem: Convolutional Sparse Coding (CSC). The sparse representation framework is a popular approach due to its desirable theoretical guarantees and the …

    maryland Repository record for Learning Along the Edge of Deep Neural Networks (opens in a new tab)

  4. Multi-directional multi-resolution modelling of HRCT images for automatic classification of diffuse lung disease

    … steps: dictionary learning, sparse coding and spatial pooling. After extracting the local features, the dictionary was learned by performing the K-SVD and Orthogonal Matching Pursuit (OMP) iteratively until the reconstruction error smaller than the stopping ruler. Then the original local …

    unsw Repository record for Multi-directional multi-resolution modelling of HRCT images for automatic classification of diffuse lung disease (opens in a new tab)

  5. Understanding perceived quality through visual representations

    … quality estimators, we analyze the role of spatial pooling and boosting in image quality assessment.

    gatech Repository record for Understanding perceived quality through visual representations (opens in a new tab)

  6. Multi-Scale Architectures for Human Pose Estimation

    … segmentation, based on a “Waterfall” Atrous Spatial Pooling architecture, that achieves a considerable accuracy increase while decreasing the number of network parameters and memory footprint. The proposed Waterfall architecture leverages the efficiency of progressive filtering in the cascade …

    rit Repository record for Multi-Scale Architectures for Human Pose Estimation (opens in a new tab)

  7. Design and Analysis of a Reconfigurable Hierarchical Temporal Memory Architecture

    … algorithms that store and recall temporal and spatial patterns. In this work, a reconfigurable and scalable HTM architecture is designed with unique pooling realizations. Virtual synapse design is proposed to address the dynamic interconnections occurring in the learning process. The …

    rit Repository record for Design and Analysis of a Reconfigurable Hierarchical Temporal Memory Architecture (opens in a new tab)

  8. Functional and anatomical properties of visual cortex in individuals with congenital loss of cone photoreceptor function and normally sighted controls

    … these two retinal pathways. We showed that spatial summation properties of the rod pathway are expressed at a cortical level and highlighted that low light levels mainly affect primary visual cortex, while extra striate areas, likely related to their increased spatial pooling properties, …

    whiterose Download PDF for Functional and anatomical properties of visual cortex in individuals with congenital loss of cone photoreceptor function and normally sighted controls (opens in a new tab)

  9. Semantic Segmentation and Change Detection in Satellite Imagery

    … two modules. PyWASP with the Waterfall Atrous Spatial Pooling (WASP) module investigates the effects of adding a feature pyramid network (FPN) to WASP. PyWASP with the improved WASP module (WASPv2) determines the effects of adding pyramid features to WASPv2. The pyramid features incorporate …

    rit Repository record for Semantic Segmentation and Change Detection in Satellite Imagery (opens in a new tab)

  10. Large-scale learning of discriminative image representations

    … framework, which learns the configuration of spatial pooling regions, as well as a discriminative linear projection onto a lower-dimensional subspace. The convexity of the corresponding optimisation problems is achieved by using convex, sparsity-inducing regularisers: the L1 norm and the …

    oxford Repository record for Large-scale learning of discriminative image representations (opens in a new tab)

  11. Figure-ground segmentation in gratings and plaids : a psychophysical and calcium imaging study in macaque monkey

    … discontinuities in orientation, contrast, color, spatial frequency, and other image properties. A large body of work has been dedicated to account for boundary detection and figure-ground segregation in experimental textures and natural images, yet it remains elusive how the well-known neural …

    texas Repository record for Figure-ground segmentation in gratings and plaids : a psychophysical and calcium imaging study in macaque monkey (opens in a new tab)

  12. Learning Depth From Images

    … This research explores rich and comprehensive spatial correspondence across images and designs three new network architectures for depth estimation whose inputs can be a single image, stereo pairs, or monocular video. First, we propose a novel semantic stereo network named SSPCV-Net, which …

    south-carolina Repository record for Learning Depth From Images (opens in a new tab)

  13. Robust Learning Architectures for Perceiving Object Semantics and Geometry

    … recent convolutional architectures employ spatial pooling to achieve scale and shift invariances, but they are still sensitive to out-of-plane rotations. Second, deep Convolutional Neural Networks (CNNs) are purely driven by data and predominantly pose the scene interpretation problem as an …

    jhu Repository record for Robust Learning Architectures for Perceiving Object Semantics and Geometry (opens in a new tab)

  14. Colour Vision in Birds : Comparing behavioural thresholds and model predictions

    … to increase contrast sensitivity at the cost of spatial resolution in dim light, so called spatial pooling. We used food containers covered with larger, smaller, more or fewer colour patches. Supporting the hypothesis, the containers covered by more colour could be discriminated in dimmer light. …

    lund Repository record for Colour Vision in Birds : Comparing behavioural thresholds and model predictions (opens in a new tab) Download PDF for Colour Vision in Birds : Comparing behavioural thresholds and model predictions (opens in a new tab)