323 citations · 1.4k across the 44 of their papers we have counts for
45 papers
Few-Shot Class-Incremental Learning from an Open-Set Perspective
Can Peng, Kun Zhao, Tianren Wang +2
The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments. The challenge of new task lea…
FaceCook: Face Generation Based on Linear Scaling Factors
Tianren Wang, Can Peng, Teng Zhang +1
With the excellent disentanglement properties of state-of-the-art generative models, image editing has been the dominant approach to control the attributes of synthesised face imag…
DIODE: Dilatable Incremental Object Detection
Can Peng, Kun Zhao, Sam Maksoud +2
To accommodate rapid changes in the real world, the cognition system of humans is capable of continually learning concepts. On the contrary, conventional deep learning models lack…
Scalable Bayesian Deep Learning with Kernel Seed Networks
Sam Maksoud, Kun Zhao, Can Peng +1
This paper addresses the scalability problem of Bayesian deep neural networks. The performance of deep neural networks is undermined by the fact that these algorithms have poorly c…
SID: Incremental Learning for Anchor-Free Object Detection via Selective and Inter-Related Distillation
Can Peng, Kun Zhao, Sam Maksoud +2
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will…
Faces à la Carte: Text-to-Face Generation via Attribute Disentanglement
Tianren Wang, Teng Zhang, Brian Lovell
Text-to-Face (TTF) synthesis is a challenging task with great potential for diverse computer vision applications. Compared to Text-to-Image (TTI) synthesis tasks, the textual descr…