English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Learning Graph Embeddings for Open World Compositional Zero-Shot Learning

MPS-Authors
/persons/resource/persons127761

Akata,  Zeynep
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

arXiv:2105.01017.pdf
(Preprint), 4MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Mancini, M., Naeem, M. F., Xian, Y., & Akata, Z. (2021). Learning Graph Embeddings for Open World Compositional Zero-Shot Learning. Retrieved from https://arxiv.org/abs/2105.01017.


Cite as: https://hdl.handle.net/21.11116/0000-0009-89C5-E
Abstract
Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions
of state and object visual primitives seen during training. A problem with
standard CZSL is the assumption of knowing which unseen compositions will be
available at test time. In this work, we overcome this assumption operating on
the open world setting, where no limit is imposed on the compositional space at
test time, and the search space contains a large number of unseen compositions.
To address this problem, we propose a new approach, Compositional Cosine Graph
Embeddings (Co-CGE), based on two principles. First, Co-CGE models the
dependency between states, objects and their compositions through a graph
convolutional neural network. The graph propagates information from seen to
unseen concepts, improving their representations. Second, since not all unseen
compositions are equally feasible, and less feasible ones may damage the
learned representations, Co-CGE estimates a feasibility score for each unseen
composition, using the scores as margins in a cosine similarity-based loss and
as weights in the adjacency matrix of the graphs. Experiments show that our
approach achieves state-of-the-art performances in standard CZSL while
outperforming previous methods in the open world scenario.