Domain-Aware Continual Zero-Shot Learning
الملخص
Modern visual systems have a wide range of potential applications in vision tasks for natural science research, such as aiding in species discovery, monitoring animals in the wild, and so on. However, real-world vision tasks may experience changes in environmental conditions, leading to shifts in how captured images are presented. To address this issue, we introduce Domain-Aware Continual Zero-Shot Learning (DACZSL), a task to recognize images of unseen categories in continuously changing domains. Accordingly, we propose a Domain-Invariant Network (DIN) to learn factorized features for shifting domains and improved textual representation for unseen classes. DIN continually learns a global shared network for domain-invariant and task-invariant features, and per-task private networks for task-specific features. Furthermore, we enhance the dual network with class-wise learnable prompts to improve class-level text representation, thereby improving zero-shot prediction of future unseen classes. To evaluate DACZSL, we introduce two benchmarks, DomainNet-CZSL and iWildCam-CZSL. Our results show that DIN significantly outperforms existing baselines by over 5% in harmonic accuracy and over 1% in backward transfer and achieves a new SoTA.
الكلمات المفتاحية
غير متوفر
التخصصات
رسائل وأطاريح مشابهة
- Inductive and Transductive Learning with Vision-Language Models in Low-Shot Regimes Maxime Zanella · 2026
- Adaptive Deep Learning for Vision and Multimodal Understanding with Heterogeneous Data Youwei Liang · 2026
- Feature Selection and Transfer Learning in Network Data: Enhancing Anomaly Detection with Zero-Shot and Few-Shot Learning Joideep Banerjee · Staffordshire University · 2025
- Advancing Computational Pathology with Multimodal Deep Learning Md. Mamunur Rahaman · 2025
- Zero-shot Learning: Recognition, Tagging, and Detection of Novel Concepts Shafin Rahman · Australian National University · 2020
- A Comprehensive Framework for Targeted Transfer Learning: Privacy-Preserving, Secure, and Efficient Domain Adaptation Sayyed Farid Ahamed · Old Dominion University · 2026
