Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
Jia Deng,Wei Dong,Richard Socher,Li-Jia Li,Kai Li,Li Fei-Fei +5 more
- pp 248-255
TLDR
A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.Abstract:
The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.read more
Citations
More filters
Proceedings ArticleDOI
Adversarial Examples for Semantic Segmentation and Object Detection
TL;DR: Zhang et al. as discussed by the authors proposed Dense Adversary Generation (DAG), which applies to the state-of-the-art networks for segmentation and detection, and found that the adversarial perturbations can be transferred across networks with different training data, based on different architectures, and even for different recognition tasks.
Posted Content
GhostNet: More Features from Cheap Operations
TL;DR: A novel Ghost module is proposed to generate more feature maps from cheap operations based on a set of intrinsic feature maps to generate many ghost feature maps that could fully reveal information underlying intrinsic features.
Proceedings ArticleDOI
Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization
Jonathan Tremblay,Aayush Prakash,David Acuna,Mark Brophy,Varun Jampani,Cem Anil,Thang To,Eric Cameracci,Shaad Boochoon,Stan Birchfield +9 more
TL;DR: This work presents a system for training deep neural networks for object detection using synthetic images that relies upon the technique of domain randomization, in which the parameters of the simulator are randomized in non-realistic ways to force the neural network to learn the essential features of the object of interest.
Proceedings ArticleDOI
An Analysis of Scale Invariance in Object Detection - SNIP
Bharat Singh,Larry S. Davis +1 more
TL;DR: Scale Normalization for Image Pyramids (SNIP) as discussed by the authors selectively back-propagates the gradients of object instances of different sizes as a function of the image scale to detect small objects.
Posted Content
Learning to Segment Object Candidates
TL;DR: In this article, a discriminative convolutional network is proposed to generate object proposals, which is trained jointly with two objectives: given an image patch, the first part outputs a class-agnostic segmentation mask, while the second part outputs the likelihood of the patch being centered on a full object.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Journal ArticleDOI
WordNet : an electronic lexical database
TL;DR: The lexical database: nouns in WordNet, Katherine J. Miller a semantic network of English verbs, and applications of WordNet: building semantic concordances are presented.
Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
TL;DR: The database contains labeled face photographs spanning the range of conditions typically encountered in everyday life, and exhibits “natural” variability in factors such as pose, lighting, race, accessories, occlusions, and background.
Principles of categorization
TL;DR: On those remote pages it is written that animals are divided into those that belong to the Emperor, and those that are trained, suckling pigs and stray dogs.
Proceedings ArticleDOI
Scalable Recognition with a Vocabulary Tree
David Nister,Henrik Stewenius +1 more
TL;DR: A recognition scheme that scales efficiently to a large number of objects and allows a larger and more discriminatory vocabulary to be used efficiently is presented, which it is shown experimentally leads to a dramatic improvement in retrieval quality.