Loading [a11y]/accessibility-menu.js
Unreliable-to-Reliable Instance Translation for Semi-Supervised Pedestrian Detection | IEEE Journals & Magazine | IEEE Xplore

Unreliable-to-Reliable Instance Translation for Semi-Supervised Pedestrian Detection


Abstract:

Generating realistic pedestrian instances in a semi-supervised setting is promising but challenging due to the limited labeled data. We propose an unreliable-to-reliable ...Show More

Abstract:

Generating realistic pedestrian instances in a semi-supervised setting is promising but challenging due to the limited labeled data. We propose an unreliable-to-reliable instance translation model (Un2Reliab) conditioned on unreliable instances which poorly align with pedestrians. Un2Reliab mainly consists of an encoder-decoder-like generative network and a discriminative network, which are jointly trained in a minimax game. We adopt regularization to ensure that the synthesized instances are semantically similar to the corresponding ground truth. Furthermore, to preserve the identities of persons, we propose another regularization to ensure that the synthesized instances associated with the same person should be consistent in appearance. As a result, Un2Reliab learns to restore the missing parts of the original instances. As a side benefit, the synthesized instances are brought into better alignment. Inclusion of the synthesized data improves both the diversity and quality of training data, which eventually leads to better generalization performance. Extensive experiments indicate that Un2Reliab is able to synthesize high-fidelity pedestrian instances and improve the previous state-of-the-art results on multiple semi-supervised pedestrian detection benchmarks.
Published in: IEEE Transactions on Multimedia ( Volume: 24)
Page(s): 728 - 739
Date of Publication: 10 February 2021

ISSN Information:

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.