Attribute Learning with Knowledge Enhanced Partial Annotations

Kongming Liang, Xinran Wang, Tao Wei, Wei Chen, Zhanyu Ma, Jun Guo

Abstract

Under limited annotation cost, large-scale attribute learning datasets only contain partial labels for each image. The conventional methods treat the un-annotated attributes as negative or ignore their loss without considering the associated knowledge. In this paper, we present a knowledge enhanced selective loss for partially labeled attribute learning. Given a visual instance, we investigate the object-attribute co-occurrence as internal knowledge to subdivide the unannotated attributes into feasible and infeasible sets. Based on that, we can enhance the model to focus on the learning of feasible un-annotated attributes and remove the distraction from the infeasible ones. Besides the internal knowledge, we adopt external knowledge to excavate the unseen object-attribute pairs. Experimental results show that our proposed loss can achieve state-of-the-art performance on the newly cleaned VAW2 dataset that contains 170,407 instances, 1763 objects, and 591 attributes. The code and VAW2 dataset are available at https://github.com/GriffinLiang/seal.
BibTeX
@inproceedings{liang2023attribute,
  author = {Kongming Liang and Xinran Wang and Tao Wei and Wei Chen and Zhanyu Ma and Jun Guo},
  title = {{Attribute Learning with Knowledge Enhanced Partial Annotations}},
  booktitle = {ICIP},
  year = {2023},
  doi = {10.1109/icip49359.2023.10222277},
}

Loading related content...

Figure