Salient instance segmentation via subitizing and clustering
نویسندگان
چکیده
منابع مشابه
Improving Salient Object Subitizing
In this study, we investigate the work of [1] on Salient Object Subitizing — the ability to quickly detect a small number of objects in an image. We firstly apply the method described by [1] with a bigger model to show that performance is improved. We than look at how data augmentation and additional data affects our system. We improve the (recently established) state-of-the-art in Salient Obje...
متن کاملS4Net: Single Stage Salient-Instance Segmentation
In this paper, we consider an interesting vision problem—salient instance segmentation. Other than producing approximate bounding boxes, our network also outputs high-quality instance-level segments. Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch. Our new branch regards not ...
متن کاملSalient Object Subitizing: Supplementary Material 1. Visualizing the CNN Subitizing Classifiers
[1] A. Karpathy. t-SNE visualization of CNN. http://cs.stanford.edu/people/karpathy/ cnnembed/. [2] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (NIPS), 2012. [3] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. ...
متن کاملPixelLink: Detecting Scene Text via Instance Segmentation
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/nontext classification and location regression. Regression plays a key role in the acquisition of bounding boxes in these methods, but it is not indispensable because text/non-text prediction can also be considered as a ...
متن کاملSemantic Instance Segmentation via Deep Metric Learning
We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together. Our similarity metric is based on a deep, fully convolutional embedding model. Our grouping method is based on selecting all points that are sufficiently similar to a set of “seed points’, chosen from a deep, fully c...
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: Neurocomputing
سال: 2020
ISSN: 0925-2312
DOI: 10.1016/j.neucom.2020.04.022