CVNov 13, 2018

Gradient Harmonized Single-stage Detector

arXiv:1811.05181v1590 citations
Originality Highly original
AI Analysis

This work addresses efficiency and accuracy issues in object detection for computer vision applications, offering a novel method to improve single-stage detectors.

The paper tackles the problem of training disharmonies in single-stage object detectors, such as imbalance between positive/negative and easy/hard examples, by proposing a gradient harmonizing mechanism (GHM) that improves mean average precision (mAP) to 41.6 on COCO test-dev, surpassing the state-of-the-art by 0.8 mAP.

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.

Code Implementations9 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes