Attributes learning network for generalized zero-shot learning

Yun, Yu; Wang, Sen; Hou, Mingzhen; Gao, Quanxue

doi:10.1016/j.neunet.2022.02.018

Cited by 14 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generating synthesized visual features alleviates the classification bias to a certain extent, but there still exist gaps among synthesized features and high-quality features, such as Redundancy-Free Feature-based Generalized Zero-Shot Learning (RFF-GZSL) [11], TF-VAEGAN [26], SE-GZSL [18], and FREE [3]. Besides, in comparison with the recent TDCSS [6], CMPN [10], DFTN [17], CvDSF [40], CMC-GAN [38], and SALN [39], Co-GZSL still achieves excellent improvements on the performance. Moreover, although the results of CE-GZSL [12] are close to our model, it exists a gap between them.…”

Section: Comparison With State-of-the-arts (Sotas)mentioning

confidence: 99%

“…Specially, a recent method TF-VAEGAN [26] rebuilds the semantic features with a cycle-consistency loss for generating semantically consistent features from the generator. Moreover, a Salient Attributes Learning Network (SALN) [39] produces distinctive and meaningful semantic representations, which is achieved under the guidance of visual features supervision. However, these methods perform the reconstruction operation in the original feature space, where discriminative information is lacking.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Co-GZSL: Feature Contrastive Optimization for Generalized Zero-Shot Learning

Li,

Zhan,

Shen

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

Generalized Zero-Shot Learning (GZSL) learns from only labeled seen classes during training but discriminates both seen and unseen classes during testing. In GZSL tasks, most of the existing methods commonly utilize visual and semantic features for training. Due to the lack of visual features for unseen classes, recent works generate real-like visual features by using semantic features. However, the synthesized features in the original feature space lack discriminative information. It is important that the synthesized visual features should be similar to the ones in the same class, but different from the other classes. One way to solve this problem is to introduce the embedding space after generating visual features. Following this situation, the embedded features from the embedding space can be inconsistent with the original semantic features. For another way, some recent methods constrain the representation by reconstructing the semantic features using the original visual features and the synthesized visual features. In this paper, we propose a hybrid GZSL model, named feature Contrastive optimization for GZSL (Co-GZSL), to reconstruct the semantic features from the embedded features, which ensures that the embedded features are close to the original semantic features indirectly by comparing reconstructed semantic features with original semantic features. In addition, to settle the problem that the synthesized features lack discrimination and semantic consistency, we introduce a Feature Contrastive Optimization Module (FCOM) and jointly utilize contrastive and semantic cycle-consistency losses in the FCOM to strengthen the intra-class compactness and the inter-class separability and to encourage the model to generate semantically consistent and discriminative visual features. By combining the generative module, the embedding module, and the FCOM, we achieve Co-GZSL. We evaluate the proposed Co-GZSL model on four benchmarks, and the experimental results indicate that our model is superior over current methods. Code is available at: https://github.com/zhanzhuxi/Co-GZSL.

show abstract

Section: Comparison With State-of-the-arts (Sotas)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Co-GZSL: Feature Contrastive Optimization for Generalized Zero-Shot Learning

Li,

Zhan,

Shen

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…However, annotating attributes can be very time-consuming, early efforts only focus on specific domains such as fashion [47,48], face [10,49], animals [1,41], posing severe limitations for real-world deployment. With the release of large-scale datasets including COCO Attributes [28], Visual Genome [17], and VAW [29], recent work considers building models for largevocabulary attributes classification [29,44]. Nonetheless, these methods only perform multi-class classification on pre-computed image patches, which not only fail to acquire object localization ability but also endure extra computation overhead due to redundant feature extraction passes.…”

Section: Related Workmentioning

confidence: 99%

OvarNet: Towards Open-vocabulary Object Attribute Recognition

Chen¹,

Jiang²,

Hu³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training stage, resembling an open-vocabulary scenario. To achieve this goal, we make the following contributions: (i) we start with a naïve two-stage approach for open-vocabulary object detection and attribute classification, termed CLIP-Attr. The candidate objects are first proposed with an offline RPN and later classified for semantic category and attributes; (ii) we combine all available datasets and train with a federated strategy to finetune the CLIP model, aligning the visual representation with attributes, additionally, we investigate the efficacy of leveraging freely available online image-caption pairs under weakly supervised learning; (iii) in pursuit of efficiency, we train a Faster-RCNN type model end-to-end with knowledge distillation, that performs class-agnostic object proposals and classification on semantic categories and attributes with classifiers generated from a text encoder; Finally, (iv) we conduct extensive experiments on VAW, MS-COCO, LSA, and OVAD datasets, and show that recog-Equal contribution. † Corresponding author. nition of semantic category and attributes is complementary for visual scene understanding, i.e., jointly training object detection and attributes prediction largely outperform existing approaches that treat the two tasks independently, demonstrating strong generalization ability to novel attributes and categories.

show abstract

Hierarchical contrastive representation for zero shot learning

Lu,

et al. 2024

Appl Intell

View full text Add to dashboard Cite

Attributes learning network for generalized zero-shot learning

Cited by 14 publications

References 12 publications

Co-GZSL: Feature Contrastive Optimization for Generalized Zero-Shot Learning

Co-GZSL: Feature Contrastive Optimization for Generalized Zero-Shot Learning

OvarNet: Towards Open-vocabulary Object Attribute Recognition

Hierarchical contrastive representation for zero shot learning

Contact Info

Product

Resources

About