Editorial: Hierarchical Object Representations in the Visual Cortex and Computer Vision

Rodríguez-Sánchez, Antonio Jose; Fallah, Mazyar; Leonardis, Aleš

doi:10.3389/fncom.2015.00142

Cited by 7 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, convolutional neural network architectures are the primary choice for most of the computer vision tasks. CNN takes inspiration in biological processes in that the connectivity pattern between neurons corresponds to the organization of the animal visual cortex (Hubel and Wiesel, 1968 ; Fukushima, 1980 ; Rodŕıguez-Sánchez et al, 2015 ). Similarly, as in the eye, individual neurons respond to stimuli from a restricted (bounded by the filter size) region of the visual field.…”

Section: Discussionmentioning

confidence: 99%

Improving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates

et al. 2020

View full text Add to dashboard Cite

Computer Tomography (CT) is an imaging procedure that combines many X-ray measurements taken from different angles. The segmentation of areas in the CT images provides a valuable aid to physicians and radiologists in order to better provide a patient diagnose. The CT scans of a body torso usually include different neighboring internal body organs. Deep learning has become the state-of-the-art in medical image segmentation. For such techniques, in order to perform a successful segmentation, it is of great importance that the network learns to focus on the organ of interest and surrounding structures and also that the network can detect target regions of different sizes. In this paper, we propose the extension of a popular deep learning methodology, Convolutional Neural Networks (CNN), by including deep supervision and attention gates. Our experimental evaluation shows that the inclusion of attention and deep supervision results in consistent improvement of the tumor prediction accuracy across the different datasets and training sizes while adding minimal computational overhead.

show abstract

Section: Discussionmentioning

confidence: 99%

Improving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Just noticeable differences (JNDs) were obtained in each condition by fitting a cumulative Gaussian separately to each observer's data (proportion of 'right first' or 'bottom first' responses as a function of target SOA) using a Levenburg-Marquardt algorithm maximum likelihood fitting procedure and multiplying the fitted standard deviation of this fit by 0.6745 (Cass & Van der Burg, 2014;Rodríguez-Sánchez, Fallah, & Leonardis, 2016). The cumulative offset parameter (equivalent to the point of subjective simultaneity; PSS) was free to vary.…”

Section: Discussionmentioning

confidence: 99%

Dynamic distractor environments reveal classic visual field anisotropies for judgments of temporal order

Cass

Burg

2018

Atten Percept Psychophys

View full text Add to dashboard Cite

Numerous studies have shown that visual performance critically depends on the stimulus' projected retinal location. For example, performance tends to be better along the horizontal relative to the vertical meridian (lateral anisotropy). Another case is the so-called upper-lower anisotropy, whereby performance is better in the upper relative to the lower hemifield. This study investigates whether temporal order judgments (TOJs) are subject to these visual field constraints. In Experiments 1 and 2, subjects reported the temporal order of two disks located along the horizontal or vertical meridians. Each target disk was surrounded by 10 black and white distractor disks, whose polarity remained unchanged (static condition) or reversed throughout the trial (dynamic condition). Results indicate that the mere presence of dynamic distractors elevated thresholds by more than a factor of four and that this elevation was particularly pronounced along the vertical meridian, evidencing the lateral anisotropy. In Experiment 3, thresholds were compared in upper, lower, left, and right visual hemifields. Results show that the threshold elevation caused by dynamic distractors was greatest in the upper visual field, demonstrating an upper-lower anisotropy. Critically, these anisotropies were evident exclusively in dynamic distractor conditions suggesting that distinct processes govern TOJ performance under these different contextual conditions. We propose that whereas standard TOJs are processed by fast low-order motion mechanisms, the presence of dynamic distractors mask these low-order motion signals, forcing observers to rely more heavily on more sluggish higher order motion processes.

show abstract

“…Brief background on 2D convolution. We do not explain the background of 2D convolution operation [33] in detail. Formally speaking, if X ∈ R 𝑀×𝑃 represents an input data matrix, and if W (l) ∈ R 𝑘 𝑙 ×𝑘 𝑙 (𝑘 𝑙 mod 2 = 1, i.e., 𝑘 𝑙 an odd number) denotes the kernel weight matrix of the 𝑙 th layer, conveniently represented as (𝑊 (𝑙) − ⌊𝑘/2⌋ , .…”

Section: Layered Convolutions For Qppmentioning

confidence: 99%

Deep-QPP: A Pairwise Interaction-based Deep Learning Model for Supervised Query Performance Prediction

Datta¹,

Ganguly²,

Greene³

et al. 2022

Preprint

View full text Add to dashboard Cite

Motivated by the recent success of end-to-end deep neural models for ranking tasks, we present here a supervised end-to-end neural approach for query performance prediction (QPP). In contrast to unsupervised approaches that rely on various statistics of document score distributions, our approach is entirely data-driven. Further, in contrast to weakly supervised approaches, our method also does not rely on the outputs from different QPP estimators. In particular, our model leverages information from the semantic interactions between the terms of a query and those in the top-documents retrieved with it. The architecture of the model comprises multiple layers of 2D convolution filters followed by a feed-forward layer of parameters. Experiments on standard test collections demonstrate that our proposed supervised approach outperforms other state-ofthe-art supervised and unsupervised approaches.

show abstract

Editorial: Hierarchical Object Representations in the Visual Cortex and Computer Vision

Cited by 7 publications

References 40 publications

Improving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates

Improving CT Image Tumor Segmentation Through Deep Supervision and Attentional Gates

Dynamic distractor environments reveal classic visual field anisotropies for judgments of temporal order

Deep-QPP: A Pairwise Interaction-based Deep Learning Model for Supervised Query Performance Prediction

Contact Info

Product

Resources

About