# SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment Source: [SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:00:55.020Z Authors: Yixin Chen, Zhuotao Tian, Pengguang Chen, Shu Liu, Jiaya Jia Published: 2022-03-02T04:24:05.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()