KIT | KIT-Bibliothek | Impressum | Datenschutz

Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning

Munir, Muhammad Akhtar; Khan, Muhammad Haris; Sarfraz, M. Saquib 1; Ali, Mohsen
1 Institut für Anthropomatik und Robotik (IAR), Karlsruher Institut für Technologie (KIT)

Abstract:

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment. This often suffers due to unwanted background and lacks class-specific alignment. A straightforward approach to promote class-level alignment is to use high confidence predictions on unlabeled domain as pseudo-labels. These predictions are often noisy since model is poorly calibrated under domain shift. In this paper, we propose to leverage model's predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment. We develop a technique to quantify predictive uncertainty on class assignments and bounding-box predictions. Model predictions with low uncertainty are used to generate pseudo-labels for self-training, whereas the ones with higher uncertainty are used to generate tiles for adversarial feature alignment. This synergy between tiling around uncertain object regions and generating pseudo-labels from highly certain object regions allows capturing both image and instance-level context during the model adaptation. ... mehr


Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2023
Sprache Englisch
Identifikator KITopen-ID: 1000168980
Umfang 13 S.
Vorab online veröffentlicht am 08.11.2023
Nachgewiesen in Dimensions
arXiv
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page