A Large-Scale Attribute Dataset for Zero-Shot Learning

Zhao, Bo; Fu, Yanwei; Liang, Rui; Wu, Jiahong; Wang, Yonggang; Wang, Yizhou

doi:10.1109/cvprw.2019.00053

Cited by 34 publications

(18 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We experiment on three datasets, Animals with Attributes 2 (AwA) [24], Large attribute (LAD) [41] and Caltech UCSD Birds (CUB) [31]. For the qualitative analysis with grounding we select 50 attributes that change their value most for the CUB, 50 attributes for AWA, and 100 attributes for the LAD dataset.…”

Section: Datasetsmentioning

confidence: 99%

Counterfactual attribute-based visual explanations for classification

Gulshad

Smeulders

2021

Int J Multimed Info Retr

View full text Add to dashboard Cite

In this paper, our aim is to provide human understandable intuitive factual and counterfactual explanations for the decisions of neural networks. Humans tend to reinforce their decisions by providing attributes and counterattributes. Hence, in this work, we utilize attributes as well as examples to provide explanations. In order to provide counterexplanations we make use of directed perturbations to arrive at the counterclass attribute values in doing so, we explain what is present and what is absent in the original image. We evaluate our method when images are misclassified into closer counterclasses as well as when misclassified into completely different counterclasses. We conducted experiments on both finegrained as well as coarsegrained datasets. We verified our attribute-based explanations method both quantitatively and qualitatively and showed that attributes provide discriminating and human understandable explanations for both standard as well as robust networks.

show abstract

Section: Datasetsmentioning

confidence: 99%

Counterfactual attribute-based visual explanations for classification

Gulshad

Smeulders

2021

Int J Multimed Info Retr

View full text Add to dashboard Cite

show abstract

“…Semantic representations. Visual attributes are the most popular semantic representations (Lampert et al, 2009;Patterson and Hays, 2012;Wah et al, 2011;Zhao et al, 2019). However, due to the need of human annotation, the largest dataset has only 717 classes.…”

Section: Related Workmentioning

confidence: 99%

Revisiting Document Representations for Large-Scale Zero-Shot Learning

Kil¹,

Chao²

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Zero-shot learning aims to recognize unseen objects using their semantic representations. Most existing works use visual attributes labeled by humans, not suitable for large-scale applications. In this paper, we revisit the use of documents as semantic representations. We argue that documents like Wikipedia pages contain rich visual information, which however can easily be buried by the vast amount of non-visual sentences. To address this issue, we propose a semi-automatic mechanism for visual sentence extraction that leverages the document section headers and the clustering structure of visual sentences. The extracted visual sentences, after a novel weighting scheme to distinguish similar classes, essentially form semantic representations like visual attributes but need much less human effort. On the Ima-geNet dataset with over 10,000 unseen classes, our representations lead to a 64% relative improvement against the commonly used ones.

show abstract

“…al. [20] employe attribute learning to detect the unseen object by the between-class attribute transfer. It demonstrates that the attributes features are shareable and can be as the intermediate representation for object recognition.…”

Section: B Attribute Learningmentioning

confidence: 99%

Scene Attribute Semantic Relational Regularization for Transport-Travel Scene Understanding

et al. 2020

View full text Add to dashboard Cite

Attribute learning has improved the performance in scene understanding and scene recognition. However, there are many attributes described by words or short texts in a static scene and traffic crowd scene. If there are two similar scenes, the semantic relationship topology structures of corresponding attribute groups of the two scenes are also homogeneity. But it is difficult to learn a semantic relation topology projection across semantic text data and visual data. To solve the problem, we construct approximate homeomorphism mapping based on the scene attributes semantic relational regularization. Hence, we propose a novel attribute semantic topological relationship regularization based scene attribute semantic learning(ARSL) method for scene semantic understanding. And we establish a transport and travel scene recognition model based on attribute semantic features which are achieved by the proposed ARSL algorithm. In order to verify the proposed method, the experiments are implemented on the static transporttravel scene dataset and dynamic transport-travel crowds scene dataset respectively. And the static transporttravel scene dataset is constructed by the SUN Attribute dataset including images and texts. However, the dynamic transport-travel crowds scene dataset is constructed through the WWW Crowd dataset including videos and texts, and the dynamic transport-travel crowd scene dataset is named as the WWW Crowd-Sub dataset. The performances of the proposed method are improved by 38.48% and 17.51% on the SUN Attribute dataset and WWW Crowd-Sub dataset respectively. The experimental results on the SUN Attribute dataset and WWW Crowd-Sub dataset demonstrate that the proposed approach has superior performance compared to state of the art. And it can be demonstrated that the performance of the proposed ARSL method is effective against static transport-travel scene and dynamic transport-travel crowd scene.

show abstract

A Large-Scale Attribute Dataset for Zero-Shot Learning

Cited by 34 publications

References 49 publications

Counterfactual attribute-based visual explanations for classification

Counterfactual attribute-based visual explanations for classification

Revisiting Document Representations for Large-Scale Zero-Shot Learning

Scene Attribute Semantic Relational Regularization for Transport-Travel Scene Understanding

Contact Info

Product

Resources

About