On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning

Anwaar, Muhammad Umer; Pan, Zhihui; Kleinsteuber, Martin

doi:10.1145/3503161.3547798

Cited by 3 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Nagarajan et al [26] build a composition space by simulating all the visual changes of attributes performed on objects. Anwaar et al [1] improve composition learning by building a composition graph. Recent approaches [19,27,38], rooted in Vision-Language Models (VLM), also adopt either of the two strategies, utilizing pre-trained VLM encoders to better encode and align images and texts.…”

Section: Related Workmentioning

confidence: 99%

Diversity-Boosted Generalization-Specialization Balancing for Zero-Shot Learning

Liu

Chang

et al. 2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

The objective of Active Learning is to strategically label a subset of the dataset to maximize performance within a predetermined labeling budget. In this study, we harness features acquired through self-supervised learning. We introduce a straightforward yet potent metric, Cluster Distance Difference, to identify diverse data. Subsequently, we introduce a novel framework, Balancing Active Learning (BAL), which constructs adaptive sub-pools to balance diverse and uncertain data. Our approach outperforms all established active learning methods on widely recognized benchmarks by 1.20%. Moreover, we assess the efficacy of our proposed framework under extended settings, encompassing both larger and smaller labeling budgets. Experimental results demonstrate that, when labeling 80% of the samples, the performance of the current SOTA method declines by 0.74%, whereas our proposed BAL achieves performance comparable to the full dataset. Codes are available at https://github.com/JulietLJY/BAL.

show abstract

Section: Related Workmentioning

confidence: 99%

Diversity-Boosted Generalization-Specialization Balancing for Zero-Shot Learning

Liu

Chang

et al. 2023

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…To compose the seen primitives into unseen compositions, two challenges must be considered. Firstly, there are semantic entanglements between objects and attributes (Atzmon et al 2021;Anwaar, Pan, and Kleinsteuber 2022). For an image labeled as ancient-building, it is hard to tell which visual features can be captured as a building, and which, as ancient.…”

Section: Introductionmentioning

confidence: 99%

Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning

Jing,

Li,

Chen

et al. 2024

AAAI

View full text Add to dashboard Cite

Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by learning from seen compositions. Composing the learned knowledge of seen primitives, i.e., attributes or objects, into novel compositions is critical for CZSL. In this work, we propose to explicitly retrieve knowledge of seen primitives for compositional zero-shot learning. We present a retrieval-augmented method, which augments standard multi-path classification methods with two retrieval modules. Specifically, we construct two databases storing the attribute and object representations of training images, respectively. For an input training/testing image, we use two retrieval modules to retrieve representations of training images with the same attribute and object, respectively. The primitive representations of the input image are augmented by using the retrieved representations, for composition recognition. By referencing semantically similar images, the proposed method is capable of recalling knowledge of seen primitives for compositional generalization. Experiments on three widely-used datasets show the effectiveness of the proposed method.

show abstract

Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning

Huang,

Gong,

Feng

et al. 2024

2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning

Cited by 3 publications

References 23 publications

Diversity-Boosted Generalization-Specialization Balancing for Zero-Shot Learning

Diversity-Boosted Generalization-Specialization Balancing for Zero-Shot Learning

Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning

Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning

Contact Info

Product

Resources

About