We revisit the one- and two-stage detector distillation tasks and present a simple and efficient semantic-aware framework to fill the gap between them. We address the pixel-level imbalance problem by designing the category anchor to produce a representative pattern for each category and regularize the topological distance between pixels and category anchors to further tighten their semantic bonds. We name our method SEA (SEmantic-aware Alignment) distillation given the nature of abstracting dense fine-grained information by semantic reliance to well facilitate distillation efficacy. SEA is well adapted to either detection pipeline and achieves new state-of-the-art results on the challenging COCO object detection task on both one- and two-stage detectors. Its superior performance on instance segmentation further manifests the generalization ability. Both 2x-distilled RetinaNet and FCOS with ResNet50-FPN outperform their corresponding 3x ResNet101-FPN teacher, arriving 40.64 and 43.06 AP, respectively. Code will be made publicly available.
@article{arxiv.2203.00862,
title = {SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment},
author = {Yixin Chen and Zhuotao Tian and Pengguang Chen and Shu Liu and Jiaya Jia},
journal= {arXiv preprint arXiv:2203.00862},
year = {2022}
}