M-RRFS: A Memory-Based Robust Region Feature Synthesizer for Zero-Shot Object Detection
With the goal to detect both the object categories appearing in the training phase and those
never have been observed before testing, zero-shot object detection (ZSD) becomes a …
never have been observed before testing, zero-shot object detection (ZSD) becomes a …
Continual Learning Improves Zero-Shot Action Recognition
SN Gowda, D Moltisanti… - Proceedings of the …, 2024 - openaccess.thecvf.com
Zero-shot learning in action recognition requires a strong ability to generalize from pre-
training and seen classes to novel unseen classes. Similarly, the area of continual learning …
training and seen classes to novel unseen classes. Similarly, the area of continual learning …
Dynamic VAEs via semantic-aligned matching for continual zero-shot learning
Abstract Continual Zero-shot Learning (CZSL) is capable of classifying unseen categories
across a sequence of tasks. However, CZSL is often plagued by the challenge of …
across a sequence of tasks. However, CZSL is often plagued by the challenge of …
PAMK: Prototype Augmented Multi-Teacher Knowledge Transfer Network for Continual Zero-Shot Learning
J Lu, S Sun - IEEE Transactions on Image Processing, 2024 - ieeexplore.ieee.org
Continual zero-shot learning (CZSL) aims to develop a model that accumulates historical
knowledge to recognize unseen tasks, while eliminating catastrophic forgetting for seen …
knowledge to recognize unseen tasks, while eliminating catastrophic forgetting for seen …
Domain-aware continual zero-shot learning
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 …
science research, such as aiding in species discovery, monitoring animals in the wild, and …