DeepAI AI Chat
Log In Sign Up

Gradient Harmonized Single-stage Detector

by   Buyu Li, et al.
The Chinese University of Hong Kong

Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i.e. the huge difference in quantity between positive and negative examples as well as between easy and hard examples. In this work, we first point out that the essential effect of the two disharmonies can be summarized in term of the gradient. Further, we propose a novel gradient harmonizing mechanism (GHM) to be a hedging for the disharmonies. The philosophy behind GHM can be easily embedded into both classification loss function like cross-entropy (CE) and regression loss function like smooth-L_1 (SL_1) loss. To this end, two novel loss functions called GHM-C and GHM-R are designed to balancing the gradient flow for anchor classification and bounding box refinement, respectively. Ablation study on MS COCO demonstrates that without laborious hyper-parameter tuning, both GHM-C and GHM-R can bring substantial improvement for single-stage detector. Without any whistles and bells, our model achieves 41.6 mAP on COCO test-dev set which surpasses the state-of-the-art method, Focal Loss (FL) + SL_1, by 0.8.


page 1

page 2

page 3

page 4


IoU-balanced Loss Functions for Single-stage Object Detection

Single-stage detectors are efficient. However, we find that the loss fun...

Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism

The loss function for bounding box regression (BBR) is essential to obje...

Adaptive Class Weight based Dual Focal Loss for Improved Semantic Segmentation

In this paper, we propose a Dual Focal Loss (DFL) function, as a replace...

Semi-Anchored Detector for One-Stage Object Detection

A standard one-stage detector is comprised of two tasks: classification ...

RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free

Recently two-stage detectors have surged ahead of single-shot detectors ...

Improved Hard Example Mining Approach for Single Shot Object Detectors

Hard example mining methods generally improve the performance of the obj...

End-to-end training of object class detectors for mean average precision

We present a method for training CNN-based object class detectors direct...