Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
3
Recurrent token mixing via GTR achieves 58.9 AP on COCO with sub-2ms latency, offering a practical, efficient alternative to quadratic self-attention for high-resolution dense prediction.
Simple fine-tuning with a parallel decoder and smart learning rate schedule lets you beat more complex meta-learning approaches in cross-domain few-shot object detection.
Compact ViTs can now rival or surpass CNN-based architectures like YOLO for edge-based object detection, instance segmentation, and pose estimation, thanks to task-specialized distillation.
