丟棄Transformer，FCN也可以實現E2E檢測

{"type":"doc","content":[{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"我們基於FCOS，首次在dense prediction上利用全卷積結構做到E2E，即無NMS後處理。我們首先分析了常見的dense prediction方法（如RetinaNet、FCOS、ATSS等），並且認爲one-to-many的label assignment是依賴NMS的關鍵。受到DETR的啓發，我們設計了一種prediction-aware one-to-one assignment方法。此外，我們還提出了3D Max Filtering以增強feature在local區域的表徵能力，並提出用one-to-many auxiliary loss加速收斂。我們的方法基本不修改模型結構，不需要更長的訓練時間，可以基於現有dense prediction方法平滑過渡。我們的方法在無NMS的情況下，在COCO數據集上達到了與有NMS的FCOS相當的性能；在代表了密集場景的CrowdHuman數據集上，我們的方法的recall超越了依賴NMS方法的理論上限。"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null},"content":[{"type":"text","text":"整體方法流程如下圖所示："}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"image","attrs":{"src":"https:\/\/static001.infoq.cn\/resource\/image\/67\/c1\/67436c182b11e6bf5afa97f183d446c1.png","alt":null,"title":"","style":[{"key":"width","value":"75%"},{"key":"bordertype","value":"none"}],"href":"","fromPaste":false,"pastePass":false}},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}},{"type":"heading","attrs":{"align":null,"level":2},"content":[{"type":"text","marks":[{"type":"strong"}],"text":"One-to-many vs. one-to-one"}]},{"type":"paragraph","attrs":{"indent":0,"number":0,"align":null,"origin":null}}]}