Noise-guided Masking for Image-based Joint-Embedding Predictive Architectures Görüntü Tabanli Ortak Gömme Mimariler için Gürültü Yönlendirmeli Maskeleme
34th Signal Processing and Communications Applications Conference, SIU 2026, İstanbul, Türkiye, 7 - 10 Temmuz 2026, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/siu71813.2026.11636521
- Basıldığı Şehir: İstanbul
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: data-independent-masking, joint-embedding predictive architecture, masked image modeling, noise-guided masking, self-supervised learning
- Boğaziçi Üniversitesi Adresli: Evet
Özet
In masked image modeling methods, both data-adaptive and data-independent masking strategies are employed. While noise-guided masking strategies that are data-independent have been observed to improve generative models such as Masked Autoencoders (MAE), their impact on non-generative frameworks remains unexplored. This work fills this gap by adapting noise-guided masking to the Image-based Joint Embedding Predictive Architecture (I-JEPA). Our method, which guides the selection of regions to mask using spectrally filtered noise improves training efficiency by 25-30% while matching or exceeding multi-block masking performance in linear probing on ImageNet-1K.