F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning

Xian, Yongqin; Sharma, Saurabh; Schiele, Bernt; Akata, Zeynep

doi:10.1109/cvpr.2019.01052

Cited by 462 publications

(389 citation statements)

References 39 publications

Supporting

Mentioning

389

Contrasting

Order By: Relevance

“…Recently, a popular approach of zero-shot classification is generating synthesized features for unseen categories. For example, the method in [44] first generated features using word embeddings and random vectors, which was further improved by later works [7,22,28,40,45]. These zero-shot classification methods generated image features without involving contextual information.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Context-aware Feature Generation For Zero-shot Semantic Segmentation

Zhou

Niu

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Existing semantic segmentation models heavily rely on dense pixelwise annotations. To reduce the annotation pressure, we focus on a challenging task named zero-shot semantic segmentation, which aims to segment unseen objects with zero annotations. This task can be accomplished by transferring knowledge across categories via semantic word embeddings. In this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet. In particular, with the observation that a pixel-wise feature highly depends on its contextual information, we insert a contextual module in a segmentation network to capture the pixel-wise contextual information, which guides the process of generating more diverse and context-aware features from semantic word embeddings. Our method achieves state-of-the-art results on three benchmark datasets for zero-shot segmentation. CCS CONCEPTS • Computing methodologies → Image segmentation.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Transferring knowledge from seen categories to unseen categories is not a new idea and has been actively studied by zero-shot learning (ZSL) [2,10,21,45]. Most ZSL methods tend to learn the mapping between visual features and semantic word embeddings or synthesize visual features for unseen categories.…”

Section: Introductionmentioning

confidence: 99%

Context-aware Feature Generation For Zero-shot Semantic Segmentation

Zhou

Niu

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Amongst different GZSL approaches, non-generative models aim to learn deterministic or stochastic functions given the semantic and the visual spaces [9,10,15,21,23,24,29,31,[37][38][39]. On the other hand, generative techniques for GZSL focus to combat the classimbalance issue in GZSL by modeling the underlying data distributions [4,12,14,16,19,27,35,36]. Notably, [35] uses WGAN [6], which is trained to generate visual samples of the seen classes from the corresponding seen class-prototypes.…”

Section: Related Workmentioning

confidence: 99%

“…[14] proposes to alleviate confusion between seen and unseen class samples and introduce feature confusion scores. [36] uses GAN and VAE to generate unseen class samples.…”

Section: Related Workmentioning

confidence: 99%

Generalized Zero-Shot Learning using Generated Proxy Unseen Samples and Entropy Separation

Gune

Banerjee

Chaudhuri

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

The recent generative model-driven Generalized Zero-shot Learning (GZSL) techniques overcome the prevailing issue of the model bias towards the seen classes by synthesizing the visual samples of the unseen classes through leveraging the corresponding semantic prototypes. Although such approaches significantly improve the GZSL performance due to data augmentation, they violate the principal assumption of GZSL regarding the unavailability of semantic information of unseen classes during training. In this work, we propose to use a generative model (GAN) for synthesizing the visual proxy samples while strictly adhering to the standard assumptions of the GZSL. The aforementioned proxy samples are generated by exploring the early training regime of the GAN. We hypothesize that such proxy samples can effectively be used to characterize the average entropy of the label distribution of the samples from the unseen classes. Further, we train a classifier on the visual samples from the seen classes and proxy samples using entropy separation criterion such that an average entropy of the label distribution is low and high, respectively, for the visual samples from the seen classes and the proxy samples. Such entropy separation criterion generalizes well during testing where the samples from the unseen classes exhibit higher entropy than the entropy of the samples from the seen classes. Subsequently, low and high entropy samples are classified using supervised learning and ZSL rather than GZSL. We show the superiority of the proposed method by experimenting on AWA1, CUB, HMDB51, and UCF101 datasets. CCS CONCEPTS • Computing methodologies → Object recognition.

show abstract

“…We compare our method, tuned-SAE, with state-of-theart method [36] and other work are compared in [24]. All compared research studies have used zero-shot learning (supervised learning) [31] [16] and semi-supervised learning [28].…”

Section: Competitorsmentioning

confidence: 99%

On Parameter Tuning in Meta-Learning for Computer Vision

Mohammadi

Arabnia

Amini

2019

2019 International Conference on Computational Science and Computational Intelligence (CSCI)

View full text Add to dashboard Cite

Learning to learn plays a pivotal role in metalearning (MTL) to obtain an optimal learning model. In this paper, we investigate image recognition for unseen categories of a given dataset with limited training information. We deploy a zero-shot learning (ZSL) algorithm to achieve this goal. We also explore the effect of parameter tuning on performance of semantic auto-encoder (SAE). We further address the parameter tuning problem for meta-learning, especially focusing on zero-shot learning. By combining different embedded parameters, we improved the accuracy of tuned-SAE. Advantages and disadvantages of parameter tuning and its application in image classification are also explored.

show abstract

F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning

Cited by 462 publications

References 39 publications

Context-aware Feature Generation For Zero-shot Semantic Segmentation

Context-aware Feature Generation For Zero-shot Semantic Segmentation

Generalized Zero-Shot Learning using Generated Proxy Unseen Samples and Entropy Separation

On Parameter Tuning in Meta-Learning for Computer Vision

Contact Info

Product

Resources

About