Automatic Image Attribute Selection for Zero-Shot Learning of Object Categories

Liu, Liangchen; Wiliem, Arnold; Chen, Shaokang; Lovell, Brian C.

doi:10.1109/icpr.2014.452

Cited by 22 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, we should select the key attributes to improve the semantic presentation. Liu, Wiliem, Chen, and Lovell (2014) proposed a novel greedy algorithm that selects attributes based on their discriminating power and reliability. Guo et al (2018) proposed selecting attributes by measuring the distributive entropy and predictability of attributes based on the training data.…”

Section: Attribute Selectionmentioning

confidence: 99%

Improving Generalization via Attribute Selection on Out-of-the-Box Data

Tsang

Liu

2020

Neural Computation

View full text Add to dashboard Cite

Zero-shot learning (ZSL) aims to recognize unseen objects (test classes) given some other seen objects (training classes) by sharing information of attributes between different objects. Attributes are artificially annotated for objects and treated equally in recent ZSL tasks. However, some inferior attributes with poor predictability or poor discriminability may have negative impacts on the ZSL system performance. This letter first derives a generalization error bound for ZSL tasks. Our theoretical analysis verifies that selecting the subset of key attributes can improve the generalization performance of the original ZSL model, which uses all the attributes. Unfortunately, previous attribute selection methods have been conducted based on the seen data, and their selected attributes have poor generalization capability to the unseen data, which is unavailable in the training stage of ZSL tasks. Inspired by learning from pseudo-relevance feedback, this letter introduces out-of-the-box data—pseudo-data generated by an attribute-guided generative model—to mimic the unseen data. We then present an iterative attribute selection (IAS) strategy that iteratively selects key attributes based on the out-of-the-box data. Since the distribution of the generated out-of-the-box data is similar to that of the test data, the key attributes selected by IAS can be effectively generalized to test data. Extensive experiments demonstrate that IAS can significantly improve existing attribute-based ZSL methods and achieve state-of-the-art performance.

show abstract

Section: Attribute Selectionmentioning

confidence: 99%

Improving Generalization via Attribute Selection on Out-of-the-Box Data

Tsang

Liu

2020

Neural Computation

View full text Add to dashboard Cite

show abstract

“…Symbol C is a nonempty collection of nonempty attribute-value pair sets, and L is the local covering of K. A more detailed explanation can be found in the work of Grzymala-Busse [53]. Figure 3 demonstrates the pseudocode of LEM2 based on the study of Liu et al [54].…”

mentioning

confidence: 99%

Research and Application of a Novel Hybrid Model Based on a Deep Neural Network Combined with Fuzzy Time Series for Energy Forecasting

Wei

Wang

et al. 2019

Energies

View full text Add to dashboard Cite

In recent years, although deep learning algorithms have been widely applied to various fields, ranging from translation to time series forecasting, researchers paid limited attention to modelling parameter optimization and the combination of the fuzzy time series. In this paper, a novel hybrid forecasting system, named CFML (complementary ensemble empirical mode decomposition (CEEMD)-fuzzy time series (FTS)-multi-objective grey wolf optimizer (MOGWO)-long short-term memory (LSTM)), is proposed and tested. This model is based on the LSTM model with parameters optimized by MOGWO, before which a fuzzy time series method involving the LEM2 (learning from examples module version two) algorithm is adopted to generate the final input data of the optimized LSTM model. In addition, the CEEMD algorithm is also used to de-noise and decompose the raw data. The CFML model successfully overcomes the nonstationary and irregular features of wind speed data and electrical power load series. Several experimental results covering four wind speed datasets and two electrical power load datasets indicate that our hybrid forecasting system achieves average improvements of 49% and 70% in wind speed and electrical power load, respectively, under the metric MAPE (mean absolute percentage error).

show abstract

Section: Introductionmentioning

confidence: 99%

“…A similar color selection approach has been adopted in [44] for object classification in Animal with Attribute (AwA) dataset. The authors in [44] proposed a greedy algorithm using Discriminative and Reliable Attribute Learning (DRAL) which selects a subset of attributes to maximize an objective function. Liu et al [55] proposed a unified framework for attribute prediction which exploits the relation between attributes to boost the performance of attribute-based learning methods.…”

Section: Introductionmentioning

confidence: 99%

Text recognition in scene image and video frame using Color Channel selection

Bhunia

Kumar

Roy

et al. 2017

Multimed Tools Appl

View full text Add to dashboard Cite

In recent years, recognition of text from natural scene image and video frame has got increased attention among the researchers due to its various complexities and challenges. Because of low resolution, blurring effect, complex background, different fonts, color and variant alignment of text within images and video frames, etc., text recognition in such scenario is difficult. Most of the current approaches usually apply a binarization algorithm to convert them into binary images and next OCR is applied to get the recognition result. In this paper, we present a novel approach based on color channel selection for text recognition from scene images and video frames. In the approach, at first, a color channel is automatically selected and then selected color channel is considered for text recognition. Our text recognition framework is based on Hidden Markov Model (HMM) which uses Pyramidal Histogram of Oriented Gradient features extracted from selected color channel. From each sliding window of a color channel our color-channel selection approach analyzes the image properties from the sliding window and then a multi-label Support Vector Machine (SVM) classifier is applied to select the color channel that will provide the best recognition results in the sliding window. This color channel selection for each sliding window has been found to be more fruitful than considering a single color channel for the whole word image. Five different features have been analyzed for multi-label SVM based color channel selection where wavelet transform based feature outperforms others. Our framework of color channel selection is script-independent. It has been tested in English (Roman) and Devanagari (Indic) scripts. We have tested our approach on English datasets (ICDAR 2003, ICDAR 2013 MSRA-TD500, IIIT5K, SVT, YVT) publicly available for both video and scene images. For Devanagari script, we collected our own dataset. The performances obtained from experimental results are encouraging and show the advantage of the proposed method.

show abstract

Automatic Image Attribute Selection for Zero-Shot Learning of Object Categories

Cited by 22 publications

References 24 publications

Improving Generalization via Attribute Selection on Out-of-the-Box Data

Improving Generalization via Attribute Selection on Out-of-the-Box Data

Research and Application of a Novel Hybrid Model Based on a Deep Neural Network Combined with Fuzzy Time Series for Energy Forecasting

Text recognition in scene image and video frame using Color Channel selection

Contact Info

Product

Resources

About