A Unified Multiplicative Framework for Attribute Learning

Liang, Kongming; Chang, Hong; Shan, Shiguang; Chen, Xilin

doi:10.1109/iccv.2015.288

Cited by 29 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This demonstrates the importance of learning the classification codewords, rather than fixing them. Note that, for codeword regularization, best results were obtained for intermediate values of β, which encourage consistency between the se- [37]. ‡ As reported by Al-Halah et al [6].…”

Section: Gains Of Regularizationsupporting

confidence: 65%

Semantically Consistent Regularization for Zero-Shot Recognition

Morgado

Vasconcelos

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

139

View full text Add to dashboard Cite

The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic subspace explained by training classes. Thus, the former is able to constrain the whole space but lacks the ability to model semantic correlations. The latter addresses this issue but leaves part of the semantic space unsupervised. This complementarity is exploited in a new convolutional neural network (CNN) framework, which proposes the use of semantics as constraints for recognition.Although a CNN trained for classification has no transfer ability, this can be encouraged by learning an hidden semantic layer together with a semantic code for classification. Two forms of semantic constraints are then introduced. The first is a loss-based regularizer that introduces a generalization constraint on each semantic predictor. The second is a codeword regularizer that favors semantic-to-class mappings consistent with prior semantic knowledge while allowing these to be learned from data. Significant improvements over the state-of-the-art are achieved on several datasets.

show abstract

Section: Gains Of Regularizationsupporting

confidence: 65%

Semantically Consistent Regularization for Zero-Shot Recognition

Morgado

Vasconcelos

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

139

View full text Add to dashboard Cite

show abstract

“…One reason is that attributes often give prominent classification performance [21], [22], [40], [41], [42]. For another reason, attribute representation is a compact way that can further describe an image by concrete words that are humanunderstandable [16], [43], [44], [45]. Various types of attributes are proposed to enrich applicable tasks and improve the performance, such as relative attributes [15], classsimilarity attributes [21], and augmented attributes [17].…”

Section: Related Workmentioning

confidence: 99%

Zero-Shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation

Long

Liu

Shen

et al. 2018

IEEE Trans. Pattern Anal. Mach. Intell.

103

View full text Add to dashboard Cite

Abstract-Sufficient training examples are the fundamental requirement for most of the learning tasks. However, collecting welllabelled training examples is costly. Inspired by Zero-shot Learning (ZSL) that can make use of visual attributes or natural language semantics as an intermediate level clue to associate low-level features with high-level classes, in a novel extension of this idea, we aim to synthesise training data for novel classes using only semantic attributes. Despite the simplicity of this idea, there are several challenges. Firstly, how to prevent the synthesised data from over-fitting to training classes? Secondly, how to guarantee the synthesised data is discriminative for ZSL tasks? Thirdly, we observe that only a few dimensions of the learnt features gain high variances whereas most of the remaining dimensions are not informative. Thus, the question is how to make the concentrated information diffuse to most of the dimensions of synthesised data. To address the above issues, we propose a novel embedding algorithm named Unseen Visual Data Synthesis (UVDS) that projects semantic features to the high-dimensional visual feature space. Two main techniques are introduced in our proposed algorithm. (1) We introduce a latent embedding space which aims to reconcile the structural difference between the visual and semantic spaces, meanwhile preserve the local structure. (2) We propose a novel Diffusion Regularisation (DR) that explicitly forces the variances to diffuse over most dimensions of the synthesised data. By an orthogonal rotation (more precisely, an orthogonal transformation), DR can remove the redundant correlated attributes and further alleviate the over-fitting problem. On four benchmark datasets, we demonstrate the benefit of using synthesised unseen data for zero-shot learning. Extensive experimental results suggest that our proposed approach significantly outperforms the state-of-the-art methods.

show abstract

“…For foreground segmentation we use DeepLabv3+ with Xception-65 backbone [13] initially trained on PAS-CAL VOC 2012 [22] and fine-tuned on HumanParsing dataset [40,41] to predict initial human body segmentation masks. We additionally employ GrabCut [54] with background/foreground model initialized by the masks to refine object boundaries on the high-resolution images.…”

Section: Methodsmentioning

confidence: 99%

Textured Neural Avatars

Shysheya

Ulyanov

Vakhitov

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

123

113

View full text Add to dashboard Cite

Figure 1: We propose a new model for neural rendering of humans. The model is trained for a single person and can produce renderings of this person from novel viewpoints (top) or in the new body pose (bottom) unseen during training. To improve generalization, our model retains explicit texture representation, which is learned alongside the rendering neural network. AbstractWe present a system for learning full-body neural avatars, i.e. deep networks that produce full-body renderings of a person for varying body pose and camera position. Our system takes the middle path between the classical graphics pipeline and the recent deep learning approaches that generate images of humans using image-to-image translation. In particular, our system estimates an explicit twodimensional texture map of the model surface. At the same time, it abstains from explicit shape modeling in 3D. Instead, at test time, the system uses a fully-convolutional network to directly map the configuration of body feature points w.r.t. the camera to the 2D texture coordinates of individual pixels in the image frame. We show that such a system is capable of learning to generate realistic renderings while being trained on videos annotated with 3D poses and foreground masks. We also demonstrate that maintaining an explicit texture representation helps our system to achieve better generalization compared to systems that use direct image-to-image translation.

show abstract

A Unified Multiplicative Framework for Attribute Learning

Cited by 29 publications

References 16 publications

Semantically Consistent Regularization for Zero-Shot Recognition

Semantically Consistent Regularization for Zero-Shot Recognition

Zero-Shot Learning Using Synthesised Unseen Visual Data with Diffusion Regularisation

Textured Neural Avatars

Contact Info

Product

Resources

About