paper-with-me

홈 › Papers

A Deep Multi-Level Network for Saliency Prediction

2016-09-05 · Marcella Cornia, Lorenzo Baraldi, Giuseppe Serra, Rita Cucchiara

This paper presents a novel deep architecture for saliency prediction. Current state of the art models for saliency prediction employ Fully Convolutional networks that perform a non-linear combination of features extracted from the last convolutional layer to predict saliency maps. We propose an architecture which, instead, combines features extracted at different levels of a Convolutional Neural Network (CNN). Our model is composed of three main blocks: a feature extraction CNN, a feature encoding network, that weights low and high level feature maps, and a prior learning network. We compare our solution with state of the art saliency models on two public benchmarks datasets. Results show that our model outperforms under all evaluation metrics on the SALICON dataset, which is currently the largest public dataset for saliency prediction, and achieves competitive results on the MIT300 benchmark.

📄 PDF Abstract BibTeX arXiv:1609.01064

Code (2)

marcellacornia/mlnet 공식 구현 pytorch
Amrit-pal-Singh/Saliency-Detection

Tasks

PredictionSaliency Prediction

Similar Papers 제목 키워드 기반

Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs

2016-08-18 · Youbao Tang, Xiangqian Wu

This paper proposes a novel saliency detection method by combining region-level saliency estimation and pixel-level saliency prediction with CNNs (denoted as CRPSD). For pixel-level saliency prediction, a fully convoluti…

PredictionSaliency DetectionSaliency Prediction

Modeling Object Dissimilarity for Deep Saliency Prediction

2021-04-08 · Bahar Aydemir, Deblina Bhattacharjee, Tong Zhang, Seungryong Kim 외

Saliency prediction has made great strides over the past two decades, with current techniques modeling low-level information, such as color, intensity and size contrasts, and high-level ones, such as attention and gaze d…

ObjectPredictionSaliency Prediction

Data Augmentation via Latent Diffusion for Saliency Prediction

2024-09-11 · Bahar Aydemir, Deblina Bhattacharjee, Tong Zhang, Mathieu Salzmann 외

Saliency prediction models are constrained by the limited diversity and quantity of labeled data. Standard data augmentation techniques such as rotating and cropping alter scene composition, affecting saliency. We propos…

Data AugmentationDiversityPredictionSaliency Prediction

Saliency Prediction for Mobile User Interfaces

2017-11-10 · Prakhar Gupta, Shubh Gupta, Ajaykrishnan Jayagopal, Sourav Pal 외

We introduce models for saliency prediction for mobile user interfaces. A mobile interface may include elements like buttons, text, etc. in addition to natural images which enable performing a variety of tasks. Saliency …

PredictionSaliency Prediction

Deep Visual Attention Prediction

2017-05-07 · journal 2017 11 · Wenguan Wang, Jianbing Shen

In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attenti…

PredictionSaliency Prediction