Papers
Topics
Authors
Recent
2000 character limit reached

CSCNET: Class-Specified Cascaded Network for Compositional Zero-Shot Learning (2403.05924v2)

Published 9 Mar 2024 in cs.CV

Abstract: Attribute and object (A-O) disentanglement is a fundamental and critical problem for Compositional Zero-shot Learning (CZSL), whose aim is to recognize novel A-O compositions based on foregone knowledge. Existing methods based on disentangled representation learning lose sight of the contextual dependency between the A-O primitive pairs. Inspired by this, we propose a novel A-O disentangled framework for CZSL, namely Class-specified Cascaded Network (CSCNet). The key insight is to firstly classify one primitive and then specifies the predicted class as a priori for guiding another primitive recognition in a cascaded fashion. To this end, CSCNet constructs Attribute-to-Object and Object-to-Attribute cascaded branches, in addition to a composition branch modeling the two primitives as a whole. Notably, we devise a parametric classifier (ParamCls) to improve the matching between visual and semantic embeddings. By improving the A-O disentanglement, our framework achieves superior results than previous competitive methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. “From red wine to red tomato: Composition with context,” in Proc. of the CVPR, 2017, pp. 1160–1169.
  2. “Adversarial fine-grained composition learning for unseen attribute-object recognition,” in Proc. of the ICCV, 2019, pp. 3740–3748.
  3. “A causal view of compositional zero-shot recognition,” in the NeurIPS, 2020.
  4. “Dual-stream contrastive learning for compositional zero-shot recognition,” IEEE Transactions on Multimedia, 2023.
  5. “Learning invariant visual representations for compositional zero-shot learning,” in Proc. of the ECCV, 2022, pp. 339–355.
  6. “Disentangling visual embeddings for attributes and objects,” in Proc. of the CVPR, 2022, pp. 13658–13667.
  7. “A decomposable causal view of compositional zero-shot learning,” IEEE Transactions on Multimedia, pp. 1–11, 2022.
  8. “Relation-aware compositional zero-shot learning for attribute-object pair recognition,” IEEE Transactions on Multimedia, vol. 24, pp. 3652–3664, 2022.
  9. “Isolating features of object and its state for compositional zero-shot learning,” IEEE Transactions on Emerging Topics in Computational Intelligence, pp. 1–13, 2023.
  10. “Learning conditional attributes for compositional zero-shot learning,” in Proc. of the CVPR, 2023, pp. 11197–11206.
  11. “Efficient estimation of word representations in vector space,” in Proc. of the ICLR, 2013.
  12. “Attributes as operators: Factorizing unseen attribute-object compositions,” in Proc. of the ECCV, 2018, pp. 172–190.
  13. “Task-driven modular networks for zero-shot compositional learning,” in Proc. of the ICCV, 2019, pp. 3592–3601.
  14. “Symmetry and group in attribute-object compositions,” in Proc. of the CVPR, 2020, pp. 11313–11322.
  15. “Open world compositional zero-shot learning,” in Proc. of the CVPR, 2021, pp. 5222–5230.
  16. “Learning graph embeddings for compositional zero-shot learning,” in Proc. of the CVPR, 2021, pp. 953–962.
  17. “Swap-reconstruction autoencoder for compositional zero-shot learning,” in Proc. of the ICME, 2023, pp. 438–443.
  18. “Siamese contrastive embedding network for compositional zero-shot learning,” in Proc. of the CVPR, 2022, pp. 9326–9335.
  19. “Discovering states and transformations in image collections,” in Proc. of the CVPR, 2015, pp. 1383–1391.
  20. “Learning attention as disentangler for compositional zero-shot learning,” in Proc. of the CVPR, 2023, pp. 15315–15324.
  21. “Deep residual learning for image recognition,” in Proc. of the CVPR, 2016, pp. 770–778.
  22. “Imagenet: A large-scale hierarchical image database,” in Proc. of the CVPR, 2009, pp. 248–255.
  23. “Enriching word vectors with subword information,” Trans. Assoc. Comput. Linguistics, vol. 5, pp. 135–146, 2017.
  24. “Adam: A method for stochastic optimization,” in Proc. of the ICLR, 2015.
  25. “Meta reconciliation normalization for lifelong person re-identification,” in ACM MM, 2022, pp. 541–549.
  26. “A memorizing and generalizing framework for lifelong person re-identification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 11, pp. 13567–13585, 2023.
  27. “Lifelong person re-identification via adaptive knowledge accumulation,” in Proc. of the CVPR, 2021, pp. 7901–7910.
  28. “Dual gaussian-based variational subspace disentanglement for visible-infrared person re-identification,” in ACM MM, 2020, pp. 2149–2158.
Citations (2)

Summary

We haven't generated a summary for this paper yet.

Slide Deck Streamline Icon: https://streamlinehq.com

Whiteboard

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.