Search papers, labs, and topics across Lattice.
School of Computer and Information Technology, Beijing Jiaotong University, China
3
0
4
Freezing your feature extractor during online category discovery leads to suboptimal performance: TALON shows how test-time adaptation can substantially boost novel class accuracy and prevent category explosion.
By warm-starting a dynamic priority queue with seen and generated unseen visual prototypes, this CZSL method significantly mitigates distribution shift at test time, outperforming existing approaches.
Amphibious robots are getting smarter and more adaptable thanks to advances in locomotion, actuation, and control, paving the way for more effective environmental monitoring and disaster response.
