Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
3
0
0
4
Sequence-aware training boosts SNN object detection performance by over 3 mAP points, revealing the untapped potential of temporal information in event-based systems.
Achieving 81.6% of fully supervised performance with just 10% labeled data, BBLP revolutionizes the efficiency of document layout re-annotation.
Overcome the Achilles' heel of event-based vision—its sensitivity to sensor parameters—with a training scheme that achieves sensor-agnostic object detection.