Incremental Deep Hidden Attribute Learning

2018 ◽  
Author(s):  
Zheng Wang ◽  
Xiang Bai ◽  
Mang Ye ◽  
Shin'ichi Satoh
Keyword(s):  
Attribute Learning

scholarly journals Operation Mode Decision of Indoor Cleaning Robot Based on Causal Reasoning and Attribute Learning

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 173376-173386
Author(s):  
Yapeng Li ◽  
Dongbo Zhang ◽  
Feng Yin ◽  
Ying Zhang
Keyword(s):  
Causal Reasoning ◽  
Operation Mode ◽  
Mode Decision ◽  
Cleaning Robot ◽  
Attribute Learning

scholarly journals Learning Personalized Attribute Preference via Multi-Task AUC Optimization

2019 ◽  
Vol 33 ◽  
pp. 5660-5667
Author(s):  
Zhiyong Yang ◽  
Qianqian Xu ◽  
Xiaochun Cao ◽  
Qingming Huang
Keyword(s):  
Wide Spectrum ◽  
Closed Form Solution ◽  
Form Solution ◽  
Learning Methods ◽  
Auc Optimization ◽  
Area Under Roc Curve ◽  
Multi Level ◽  
Generalization Bound ◽  
Attribute Learning ◽  
Task Parameter

Traditionally, most of the existing attribute learning methods are trained based on the consensus of annotations aggregated from a limited number of annotators. However, the consensus might fail in settings, especially when a wide spectrum of annotators with different interests and comprehension about the attribute words are involved. In this paper, we develop a novel multi-task method to understand and predict personalized attribute annotations. Regarding the attribute preference learning for each annotator as a specific task, we first propose a multi-level task parameter decomposition to capture the evolution from a highly popular opinion of the mass to highly personalized choices that are special for each person. Meanwhile, for personalized learning methods, ranking prediction is much more important than accurate classification. This motivates us to employ an Area Under ROC Curve (AUC) based loss function to improve our model. On top of the AUC-based loss, we propose an efficient method to evaluate the loss and gradients. Theoretically, we propose a novel closed-form solution for one of our non-convex subproblem, which leads to provable convergence behaviors. Furthermore, we also provide a generalization bound to guarantee a reasonable performance. Finally, empirical analysis consistently speaks to the efficacy of our proposed method.

scholarly journals SAL-Net: Self-Supervised Attribute Learning for Object Recognition and Segmentation

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Shu Yang ◽  
JingWang ◽  
Sheeraz Arif ◽  
Minli Jia ◽  
Shunan Zhong
Keyword(s):  
Object Recognition ◽  
Image Classification ◽  
Semantic Segmentation ◽  
Experimental Results ◽  
Loss Functions ◽  
Learning Methods ◽  
Object Region ◽  
Triplet Loss ◽  
Attribute Learning ◽  
The Relationship

Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined attributes are not capable enough of providing enough description. This paper proposes a self-supervised attribute learning (SAL) method, which automatically generates attribute descriptions by differentially occluding the object region to deal with the above problems. The relationship between attributes is formulated with triplet loss functions and is utilized to supervise the CNN. Attribute learning is used as an auxiliary task of a multitask image classification and segmentation network, in which self-supervision of attributes motivates the CNN to learn more discriminative features for the main semantic tasks. Experimental results on public benchmarks CUB-2011 and Pascal VOC show that the proposed SAL-Net can obtain more accurate classification and segmentation results without additional annotations. Moreover, the SAL-Net is embedded into a multiobject recognition and segmentation system, which realizes instance-aware semantic segmentation with the help of a region proposal algorithm and a fusion nonmaximum suppression algorithm.

Sign in / Sign up

Export Citation Format

Share Document