Supplementary Material for Fast Zero-Shot Image Tagging
نویسندگان
چکیده
We present another set of experiments conducted on the widely used IAPRTC-12 [6] dataset. We use the same tag annotation and image training-test split as described in [7] for our experiments. There are 291 unique tags and 19627 images in IAPRTC12. The dataset is split to 17341 training images and 2286 testing images. We further separate 15% from the training images as our validation set. Table 1: Comparison results of the conventional image tagging with 291 tags on IAPRTC-12.
منابع مشابه
Deep Multiple Instance Learning for Zero-shot Image Tagging
In-line with the success of deep learning on traditional recognition problem, several end-to-end deep models for zero-shot recognition have been proposed in the literature. These models are successful to predict a single unseen label given an input image, but does not scale to cases where multiple unseen objects are present. In this paper, we model this problem within the framework of Multiple ...
متن کاملSupplementary Material: An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
– Section 1: Hyper-parameter tuning strategies (Section 4.2 of the main text). – Section 2: Novelty detection approaches: details and additional results (Section 4.3 and 5.2 of the main text). – Section 3: Comparison between zero-shot learning approaches: additional ZSL algorithm, dataset, and results (Section 5 of the main text). – Section 4: Analysis on (generalized) zero-shot learning: detai...
متن کاملZero-shot recognition with unreliable attributes
In this document, we provide supplementary material for our NIPS 2014 paper “Zero-Shot Recognition with Unreliable Attributes”. Sec 1 shows how unlearnable attributes are avoided by our method. Sec 2 discusses the details of the signature uncertainty model introduced in Sec 3.2.3 of the paper. Sec 3 gives additional details for our controlled noise experiments (Sec 4.1 of the paper). Sec 4 list...
متن کاملComparison the Accuracy of Fetal Brain Extraction from T2-Half-Fourier Acquisition Single-Shot Turbo Spin-Echo (HASTE) MR Image with T2-True Fast Imaging with Steady State Free Precession (TRUFI) MR Image by Level Set Algorithm
Background Access to appropriate images of fetal brain can greatly assist to diagnose of probable abnormalities. The aim of this study was to compare the suitability of T2-True Fast Imaging with Steady State Free Precession (T2-TRUFI), and T2-Half-Fourier Acquisition Single-Shot Turbo Spin-Echo (T2- HASTE( magnetic resonance imaging (MRI) to extract the fetal brain using the level set algorithm...
متن کاملImproving zero-shot learning by mitigating the hubness problem
The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words associated to the nearest neighbours of the mapped vectors are used as their linguistic labels. We show that the neighbourhoods of the mapped elements are strongly polluted by hubs, v...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016