Search Results for author:
Found 4 papers, 2 papers with code
CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation
Deep Neural Networks (DNNs) are widely used for visual classification tasks, but their complex computation process and black-box nature hinder decision transparency and interpretability.
ChatGPT-guided Semantics for Zero-shot Learning
Then, we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT.
Prompt-guided Scene Generation for 3D Zero-Shot Learning
To address this problem, we propose a prompt-guided 3D scene generation and supervision method that augments 3D data to learn the network better, exploring the complex interplay of seen and unseen objects.
Rethinking Task-Incremental Learning Baselines
A common goal of task-incremental methods is to design a network that can operate on minimal size, maintaining decent performance.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
