One-Stage Object Detection Models


Introduced by Ge et al. in YOLOX: Exceeding YOLO Series in 2021

YOLOX is a single-stage object detector that makes several modifications to YOLOv3 with a DarkNet53 backbone. Specifically, YOLO’s head is replaced with a decoupled one. For each level of FPN feature, we first adopt a 1 × 1 conv layer to reduce the feature channel to 256 and then add two parallel branches with two 3 × 3 conv layers each for classification and regression tasks respectively.

Additional changes include adding Mosaic and MixUp into the augmentation strategies to boost YOLOX’s performance. The anchor mechanism is also removed so YOLOX is anchor-free. Lastly, SimOTA for label assignment -- where label assignment is formulated as an optimal transport problem via a top-k strategy.

Source: YOLOX: Exceeding YOLO Series in 2021


Paper Code Results Date Stars