LabelEnc: A New Intermediate Supervision Method for Object Detection

TL;DR

LabelEnc introduces a novel label encoding method as intermediate supervision to enhance object detection training, improving performance without additional inference cost.

Contribution

The paper proposes a new label encoding function and a two-step training process to provide auxiliary supervision, boosting object detection accuracy.

Findings

Improves detection accuracy by around 2% on COCO dataset.

Applicable to both one-stage and two-stage detection frameworks.

Auxiliary structures are only used during training, incurring no inference overhead.

Abstract

In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems. The key idea is to introduce a novel label encoding function, mapping the ground-truth labels into latent embedding, acting as an auxiliary intermediate supervision to the detection backbone during training. Our approach mainly involves a two-step training procedure. First, we optimize the label encoding function via an AutoEncoder defined in the label space, approximating the "desired" intermediate representations for the target object detector. Second, taking advantage of the learned label encoding function, we introduce a new auxiliary loss attached to the detection backbones, thus benefiting the performance of the derived detector. Experiments show our method improves a variety of detection systems by around 2% on COCO dataset, no matter one-stage or two-stage frameworks. Moreover, the auxiliary structures only exist during training, i.e. it is completely cost-free in inference time. Code is available at: https://github.com/megvii-model/LabelEnc