Normalization Calibration (NorCal) for Long-Tailed Object Detection and Instance Segmentation

Last update: Dec 25, 2022

Related tags

Deep Learning NorCal

Overview

NorCal

Normalization Calibration (NorCal) for Long-Tailed Object Detection and Instance Segmentation

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation.

Advances in Neural Information Processing Systems (NeurIPS), 2021.

Tai-Yu Pan*, Cheng Zhang*, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao.

Introduction

Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the long-tailed setting. Existing methods address this issue mostly during training, e.g., by re-sampling or re-weighting.

In this paper, we investigate a largely overlooked approach -- post-processing calibration of confidence scores. We propose NorCal, Normalized Calibration for long-tailed object detection and instance segmentation, a simple and straightforward recipe that reweighs the predicted scores of each class by its training sample size. We show that separately handling the background class and normalizing the scores over classes for each proposal are keys to achieving superior performance. On the LVIS dataset, NorCal can effectively improve nearly all the baseline models not only on rare classes but also on common and frequent classes. Finally, we conduct extensive analysis and ablation studies to offer insights into various modeling choices and mechanisms of our approach.

Installation

Install Detectron2 following the instructions.

Evaluation

Model evaluation can be done similarly:

cd /path/to/detectron2/projects/NorCal
python train_net.py --config-file configs/lvis_v0.5_mask_rcnn_R_50_FPN.yaml --eval-only MODEL.WEIGHTS /path/to/model_checkpoint TEST.CALIBRATION.GAMMA gamma

Citation

Please cite with the following bibtex if you find it useful.

@inproceedings{pan2021norcal,
  title={On Model Calibration for Long-Tailed Object Detection and Instance Segmentation},
  author={Pan, Tai-Yu and Zhang, Cheng and Li, Yandong and Hu, Hexiang and Xuan, Dong and Changpinyo, Soravit and Gong, Boqing and Chao, Wei-Lun},
  booktitle = {NeurIPS},
  year={2021}
}

You might also like...

Complete-IoU (CIoU) Loss and Cluster-NMS for Object Detection and Instance Segmentation (YOLACT)

Complete-IoU Loss and Cluster-NMS for Improving Object Detection and Instance Segmentation. Our paper is accepted by IEEE Transactions on Cybernetics

290 Dec 25, 2022

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Mask R-CNN for Object Detection and Segmentation This is an implementation of Mask R-CNN on Python 3, Keras, and TensorFlow. The model generates bound

22.5k Jan 4, 2023

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation This paper has been accepted and early accessed

39 Sep 20, 2022

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

Swin Transformer for Object Detection This repo contains the supported code and configuration files to reproduce object detection results of Swin Tran

1.4k Dec 30, 2022

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Comments

About the setting of Gamma using Multiple Binary Sigmoid Classifiers

Hi, @czhang0528. Thanks for the open-source code and the interesting idea of Normalized Calibration! According to the NueurIPS paper, it seems that $a_c=N_c^{\gamma}$. However, $\gamma$ was set to 0 in the model config. Could you please give me some advises on the selection of $\gamma$ on Multiple Binary Sigmoid Classifiers? THX
enhancement

opened by HolmesShuan 0

Normalization Calibration (NorCal) for Long-Tailed Object Detection and Instance Segmentation

Related tags

Overview

NorCal

Normalization Calibration (NorCal) for Long-Tailed Object Detection and Instance Segmentation

Introduction

Installation

Evaluation

Citation

You might also like...

Complete-IoU (CIoU) Loss and Cluster-NMS for Object Detection and Instance Segmentation (YOLACT)

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Object detection and instance segmentation toolkit based on PaddlePaddle.

Res2Net for Instance segmentation and Object detection using MaskRCNN

Pytorch implementation for "Adversarial Robustness under Long-Tailed Distribution" (CVPR 2021 Oral)

Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)

Comments

About the setting of Gamma using Multiple Binary Sigmoid Classifiers

Owner

Tai-Yu (Daniel) Pan

Improving Calibration for Long-Tailed Recognition (CVPR2021)

Exploring Classification Equilibrium in Long-Tailed Object Detection, ICCV2021

The official repo of the CVPR2021 oral paper: Representative Batch Normalization with Feature Calibration

TorchDistiller - a collection of the open source pytorch code for knowledge distillation, especially for the perception tasks, including semantic segmentation, depth estimation, object detection and instance segmentation.

Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization

HINet: Half Instance Normalization Network for Image Restoration

Official implementation of "One-Shot Voice Conversion with Weight Adaptive Instance Normalization".

[CVPR 2021] Region-aware Adaptive Instance Normalization for Image Harmonization

Unofficial pytorch implementation of 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization'

Half Instance Normalization Network for Image Restoration