3 papers
cs.LG2025
Vector Quantization Prompting for Continual Learning
Li Jiao, Qiuxia Lai, Yu Li +1
Continual learning requires to overcome catastrophic forgetting when training a single model on a sequence of tasks. Recent top-performing approaches are prompt-based methods that…
cs.CV2025
Information Bottleneck Approach to Spatial Attention Learning
Qiuxia Lai, Yu Li, Ailing Zeng +3
The selective visual attention mechanism in the human visual system (HVS) restricts the amount of information to reach visual awareness for perceiving natural scenes, allowing near…
cs.CV2024
Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis
Muxi Chen, Yi Liu, Jian Yi +5
In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework c…