#saliency

[totoshappylife]

HSOD-BIT-V2: A New Challenging Benchmark

Excerpt from PDF: HSOD-BIT-V2: A New Challenging Benchmark for Hyperspectral Salient Object Detection Yuhao Qiu, Shuyan Bai, Tingfa Xu†, Peifu Liu, Haolin Qin, Jianan Li† Beijing Institute of Technology Abstract Salient Object Detection (SOD) is crucial in computer vi- sion, yet RGB-based methods face limitations in challeng- ing scenes, such as small objects and similar color features.…

HSOD-BIT-V2: A New Challenging Benchmark

[anima-virtuosa]

saliency GOOPAWS!!!

[anima-virtuosa]

elongated

[dberga]

Publication in Neural Computation 34 (2)

Lateral connections in the primary visual cortex (V1) have long been hypothesized to be responsible of several visual processing mechanisms such as brightness induction, chromatic induction, visual discomfort and bottom-up visual attention (also named saliency). Many computational models have been developed to independently predict these and other visual processes, but no computational model has been able to reproduce all of them simultaneously. In this work we show that a biologically plausible computational model of lateral interactions of V1 is able to simultaneously predict saliency and all the aforementioned visual processes. Our model's (NSWAM) architecture is based on Pennachio's neurodynamic model of lateral connections of V1. It is defined as a network of firing rate neurons, sensitive to visual features such as brightness, color, orientation and scale. We tested NSWAM saliency predictions using images from several eye tracking datasets. We show that accuracy of predictions, using shuffled metrics, obtained by our architecture is similar to other state-of-the-art computational methods, particularly with synthetic images (CAT2000-Pattern & SID4VAM) which mainly contain low level features. Moreover, we outperform other biologically-inspired saliency models that are specifically designed to exclusively reproduce saliency. Hence, we show that our biologically plausible model of lateral connections can simultaneously explain different visual proceses present in V1 (without applying any type of training or optimization and keeping the same parametrization for all the visual processes). This can be useful for the definition of a unified architecture of the primary visual cortex.

Link to paper: https://direct.mit.edu/neco/article-abstract/34/2/378/108538/A-Neurodynamic-Model-of-Saliency-Prediction-in-V1?redirectedFrom=fulltext Preprint: https://arxiv.org/abs/1811.06308 Code: https://github.com/dberga/NSWAM

[dberga]

Publication in Pattern Recognition Letters 150 “Saliency for free: Saliency prediction as a side-effect of object recognition”

Accepted publication in PRL 150.

In this paper, we evaluate the accuracy of the saliency maps that are produced as a side-effect of object recognition. Additionally, we also evaluate the usage of supervised and unsupervised CB in our framework. We show that the CB improves in most datasets where the CB is more present. To summarize, our main contributions are: • We demonstrate that it is possible to obtain accurate saliency maps by training an object recognition network endowed with a saliency branch. Our method does not require any saliency ground truth data. • We include an extensive study of the effect of center bias on the results. • Extensive experiments performed on real and synthetic image datasets show that highly accurate saliency maps are obtained. Our method obtains competitive results on several standard benchmark datasets and the new state-ofthe-art on the CAT2000 dataset.

Link to Paper: https://www.sciencedirect.com/science/article/abs/pii/S0167865521001987

Preprint: https://arxiv.org/pdf/2107.09628.pdf

[dberga]

Accepted paper in VISAPP 16(4) “Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains”

Accepted paper in “Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: VISAPP”.

In this paper, we address the major drawback of SMIC, by implementing a hallucination mechanism in order to remove the requirement for providing saliency images for training obtained using one of the existing algorithms. In other words, we show that the explicit saliency branch which requires training on a saliency image dataset, can be replaced with a branch which is trained end-to-end for the task of image classification (for which no saliency dataset is required). We replace the saliency image with the input RGB image. We then pre-train this network for the task of image classification using a subset from ImageNet validation dataset. During this process, the saliency branch will learn to identify which regions are more discriminative. In a second phase, we initialize the weights of the saliency branch with these pre-trained weights. We then train the system end-to-end on the fine-grained dataset using only the RGB images. Results show that the saliency branch improves fine-grained recognition significantly, especially for domains with few training images. We briefly summarize below our main contributions: • we propose an approach which hallucinates saliency maps that are fused together with the RGB modality via a modulation process, • our method does not require any saliency maps for training (like in these works [Murabito et al., 2018, Flores et al., 2019]) but instead is trained indirectly in an end-to-end fashion by training the network for image classification, • our method improves classification accuracy on three fine-grained datasets, especially for domains with limited data.

Paper: https://arxiv.org/pdf/2007.12562.pdf

[innonurse]

Bioclinica Acquires Saliency to Accelerate Digital Diagnostic Development

Bioclinica, an integrated solutions provider of clinical life science and technology expertise, today announced that it has acquired Silicon Valley-based Saliency. Bioclinica will integrate the company's advanced AI technology into its Imaging Platform to support a growing portfolio of pharmaceutical and medical device clients. The integration will dramatically accelerate image QC and interpretation, enabling rapid development of digital diagnostics and digital therapeutics.

[dberga]

Publication in Neurocomputing 417 “Modeling Bottom-Up and Top-Down Attention with a Neurodynamic Model of V1”

Title: Modeling Bottom-Up and Top-Down Attention with a Neurodynamic Model of V1

Abstract: Previous studies suggested that lateral interactions of V1 cells are responsible, among other visual effects, of bottom-up visual attention (alternatively named visual salience or saliency). Our objective is to mimic these connections with a neurodynamic network of firing-rate neurons in order to predict visual attention. Early visual subcortical processes (i.e. retinal and thalamic) are functionally simulated. An implementation of the cortical magnification function is included to define the retinotopical projections towards V1, processing neuronal activity for each distinct view during scene observation. Novel computational definitions of top-down inhibition (in terms of inhibition of return, oculomotor and selection mechanisms), are also proposed to predict attention in Free-Viewing and Visual Search tasks. Results show that our model outpeforms other biologically inspired models of saliency prediction while predicting visual saccade sequences with the same model. We also show how temporal and spatial characteristics of saccade amplitude and inhibition of return can improve prediction of saccades, as well as how distinct search strategies (in terms of feature-selective or category-specific inhibition) can predict attention at distinct image contexts.

Link: https://www.sciencedirect.com/science/article/abs/pii/S0925231220311553

DOI:   10.1016/j.neucom.2020.07.047

Preprints (draft version): https://arxiv.org/abs/1904.02741 https://www.biorxiv.org/content/10.1101/590174

Code and Data: https://github.com/dberga/NSWAM