Decoupled Gradient Harmonized Detector for Partial Annotation: Application to Signet Ring Cell Detection
arXiv:2004.04455
Abstract
Early diagnosis of signet ring cell carcinoma dramatically improves the survival rate of patients. Due to lack of public dataset and expert-level annotations, automatic detection on signet ring cell (SRC) has not been thoroughly investigated. In MICCAI DigestPath2019 challenge, apart from foreground (SRC region)-background (normal tissue area) class imbalance, SRCs are partially annotated due to costly medical image annotation, which introduces extra label noise. To address the issues simultaneously, we propose Decoupled Gradient Harmonizing Mechanism (DGHM) and embed it into classification loss, denoted as DGHM-C loss. Specifically, besides positive (SRCs) and negative (normal tissues) examples, we further decouple noisy examples from clean examples and harmonize the corresponding gradient distributions in classification respectively. Without whistles and bells, we achieved the 2nd place in the challenge. Ablation studies and controlled label missing rate experiments demonstrate that DGHM-C loss can bring substantial improvement in partially annotated object detection.
arXiv commentaccepted to Neurocomputing; 1st runner up of MICCAI DigestPath2019 challenge
References in corpus (11)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Distilling the Knowledge in a Neural Network
- Deep Residual Learning for Image Recognition
- Training Deep Neural Networks on Noisy Labels with Bootstrapping
- MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
- Regularizing Neural Networks by Penalizing Confident Output Distributions
- LSDA: Large Scale Detection Through Adaptation
- Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix
- Soft Sampling for Robust Object Detection
- Signet Ring Cell Detection With a Semi-supervised Learning Framework
- PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track