Goto

Collaborating Authors

 Africa



Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection

Neural Information Processing Systems

Loss and reparameterization techniques to tackle IVLOD without incurring a significant increase in memory usage. Comprehensive experiments on COCO and ODinW-13 datasets demonstrate that ZiRa effectively safeguards the zero-shot generalization ability of VLODMs while continuously adapting to new tasks. Specifically, after training on ODinW-13 datasets, ZiRa exhibits superior performance compared to CL-DETR and iDETR, boosting zero-shot generalizabil-ity by substantial 13.91 and 8.74 AP, respectively.




Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling Wei T ang

Neural Information Processing Systems

Prophet inequality concerns a basic optimal stopping problem and states that simple threshold stopping policies -- i.e., accepting the first reward larger than a certain threshold -- can achieve tight