Mesh Saliency via Weakly Supervised Classification-for-Saliency CNN
نویسندگان
چکیده
منابع مشابه
Distinct Class-Specific Saliency Maps for Weakly Supervised Semantic Segmentation
Improved points (each point contributes 1~3pt improvement) Fully Convolutional Net Guided back propagation [2] Use the derivatives of multiple intermediate layers Aggregate multi-scale class saliency maps (3 scales) Assumption Raw saliency maps are affected by both class-specific saliency and generic object-ness The degree of class saliency factors should be larger than the generic object-ness ...
متن کاملBeyond Universal Saliency: Personalized Saliency Prediction with Multi-task CNN
Saliency detection is a long standing problem in computer vision. Tremendous efforts have been focused on exploring a universal saliency model across users despite their differences in gender, race, age, etc. Yet recent psychology studies suggest that saliency is highly specific than universal: individuals exhibit heterogeneous gaze patterns when viewing an identical scene containing multiple s...
متن کاملMesh Saliency Analysis via Local Curvature Entropy
We present a novel approach for estimating mesh saliency. Our method is fast, flexible, and easy to implement. By applying the well-known concept of Shannon entropy to 3D mesh data, we obtain an efficient method to determine mesh saliency. Comparing our method to the most recent, state-of-the-art approach, we show that results of at least similar quality can be achieved within a fraction of the...
متن کاملWeakly Supervised Saliency Detection with A Category-Driven Map Generator
Top-down saliency detection aims to highlight the regions of a specific object category, and typically relies on pixel-wise annotated training data. In this paper, we address the high cost of collecting such training data by presenting a weakly supervised approach to object saliency detection, where only image-level labels, indicating the presence or absence of a target object in an image, are ...
متن کاملMesh saliency with global rarity
Reliable estimation of visual saliency is helpful to guide many computer graphics tasks including shape matching, simplification, segmentation, etc. Inspired by basic principles induced by psychophysics studies, we propose a novel approach for computing saliency for 3D mesh surface considering both local contrast and global rarity. First, a multi-scale local shape descriptor is introduced to ca...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Visualization and Computer Graphics
سال: 2021
ISSN: 1077-2626,1941-0506,2160-9306
DOI: 10.1109/tvcg.2019.2928794