Elimination of Non-Novel Segments at Multi-Scale for Few-Shot Segmentation

Creative Commons License

Kayabasi A., Tufekci G., ULUSOY İ.

23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023, Hawaii, Amerika Birleşik Devletleri, 3 - 07 Ocak 2023, ss.2558-2566 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/wacv56688.2023.00259
  • Basıldığı Şehir: Hawaii
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.2558-2566
  • Anahtar Kelimeler: Algorithms: Machine learning architectures, and algorithms (including transfer), Biomedical/healthcare/medicine, formulations, Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning)
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

Few-shot segmentation aims to devise a generalizing model that segments query images from unseen classes during training with the guidance of a few support images whose class tally with the class of the query. There exist two domain-specific problems mentioned in the previous works, namely spatial inconsistency and bias towards seen classes. Taking the former problem into account, our method compares the support feature map with the query feature map at multi scales to become scale-agnostic. As a solution to the latter problem, a supervised model, called as base learner, is trained on available classes to accurately identify pixels belonging to seen classes. Hence, subsequent meta learner has a chance to discard areas belonging to seen classes with the help of an ensemble learning model that coordinates meta learner with the base learner. We simultaneously address these two vital problems for the first time and achieve state-of-the-art performances on both PASCAL-5i and COCO-20i datasets.