Home

Awesome

Simple-does-it-weakly-supervised-instance-and-semantic-segmentation

There are five weakly supervised networks in Simple Does It: Weakly Supervised Instance and Semantic Segmentation, by Khoreva et al. (CVPR 2017). Respectively, Naive, Box, Box^i, Grabcut+, M∩G+. All of them use cheap-to-generate label, bounding box, during training and don't need other informations except image during testing.

This repo contains a TensorFlow implementation of Grabcut version of semantic segmentation.

My Environment

Environment 1

Environment 2

Downloading the VOC12 dataset

Setup Dataset

My directory structure

./Simple_does_it/
├── Dataset
│   ├── Annotations
│   ├── CRF_masks
│   ├── CRF_pairs
│   ├── Grabcut_inst
│   ├── Grabcut_pairs
│   ├── JPEGImages
│   ├── Pred_masks
│   ├── Pred_pairs
│   ├── SegmentationClass
│   └── Segmentation_label
├── Model
│   ├── Logs
│   └── models
├── Parser_
├── Postprocess
├── Preprocess
└── Util

VOC2012 directory structure

VOCtrainval_11-May-2012
└── VOCdevkit
    └── VOC2012
        ├── Annotations
        ├── ImageSets
        │   ├── Action
        │   ├── Layout
        │   ├── Main
        │   └── Segmentation
        ├── JPEGImages
        ├── SegmentationClass
        └── SegmentationObject

mv {PATH}/VOCtrainval_11-May-2012/VOCdevkit/VOC2012/Annotations/* {PATH}/Simple_does_it/Dataset/Annotations/ 

mv {PATH}/VOCtrainval_11-May-2012/VOCdevkit/VOC2012/JPEGImages/* {PATH}/Simple_does_it/Dataset/JPEGImages/

mv {PATH}/VOCtrainval_11-May-2012/VOCdevkit/VOC2012/SegmentationClass/* {PATH}/Simple_does_it/Dataset/SegmentationClass/

Demo (See Usage for more details)

Download pretrain model training on VOC12 (train set size: 1464)

setCRFmIoU
trainX64.93%
trainO66.90%
valX39.03%
valO42.54%

Download pretrain model training on VOC12 + SBD (train set size: 10582)

setCRFmIoU
trainX66.87%
trainO68.21%
valX51.90%
valO54.52%

Training (See Usage for more details)

Download pretrain vgg16

Extract annotations from 'Annotations' according to 'train.txt' or 'voc_train.txt' for VOC12 + SDB or VOC12

Generate label for training by 'grabcut.py'

Train network

Testing (See Usage for more details)

Test network

Performance (See Usage for more details)

Evaluate mIoU and IoU

Usage

Parser_/parser.py

Util/divied.py

usage: divied.py [-h] [--dataset DATASET] [--img_dir_name IMG_DIR_NAME]
                 [--train_set_ratio TRAIN_SET_RATIO]
                 [--train_set_name TRAIN_SET_NAME]
                 [--test_set_name TEST_SET_NAME]

optional arguments:
  -h, --help            show this help message and exit
  --dataset DATASET     path to dataset (default: Util/../Parser_/../Dataset)
  --img_dir_name IMG_DIR_NAME
                        name for image directory (default: JPEGImages)
  --train_set_ratio TRAIN_SET_RATIO
                        ratio for training set, [0,10] (default: 7)
  --train_set_name TRAIN_SET_NAME
                        name for training set (default: train.txt)
  --test_set_name TEST_SET_NAME
                        name for testing set (default: val.txt)

Dataset/make_train.py

usage: make_train.py [-h] [--dataset DATASET]
                     [--train_set_name TRAIN_SET_NAME]
                     [--ann_dir_name ANN_DIR_NAME]
                     [--train_pair_name TRAIN_PAIR_NAME]

optional arguments:
  -h, --help            show this help message and exit
  --dataset DATASET     path to dataset (default:
                        Dataset/../Parser_/../Dataset)
  --train_set_name TRAIN_SET_NAME
                        name for training set (default: train.txt)
  --ann_dir_name ANN_DIR_NAME
                        name for annotation directory (default: Annotations)
  --train_pair_name TRAIN_PAIR_NAME
                        name for training pair (default: train_pairs.txt)

Preprocess/grabcut.py

usage: grabcut.py [-h] [--dataset DATASET] [--img_dir_name IMG_DIR_NAME]
                  [--train_pair_name TRAIN_PAIR_NAME]
                  [--grabcut_dir_name GRABCUT_DIR_NAME]
                  [--img_grabcuts_dir IMG_GRABCUTS_DIR]
                  [--pool_size POOL_SIZE] [--grabcut_iter GRABCUT_ITER]
                  [--label_dir_name LABEL_DIR_NAME]

optional arguments:
  -h, --help            show this help message and exit
  --dataset DATASET     path to dataset (default:
                        ./Preprocess/../Parser_/../Dataset)
  --img_dir_name IMG_DIR_NAME
                        name for image directory (default: JPEGImages)
  --train_pair_name TRAIN_PAIR_NAME
                        name for training pair (default: train_pairs.txt)
  --grabcut_dir_name GRABCUT_DIR_NAME
                        name for grabcut directory (default: Grabcut_inst)
  --img_grabcuts_dir IMG_GRABCUTS_DIR
                        name for image with grabcuts directory (default:
                        Grabcut_pairs)
  --pool_size POOL_SIZE
                        pool for multiprocess (default: 4)
  --grabcut_iter GRABCUT_ITER
                        grabcut iteration (default: 3)
  --label_dir_name LABEL_DIR_NAME
                        name for label directory (default: Segmentation_label)

Model/model.py

usage: model.py [-h] [--dataset DATASET] [--set_name SET_NAME]
                [--label_dir_name LABEL_DIR_NAME]
                [--img_dir_name IMG_DIR_NAME] [--classes CLASSES]
                [--batch_size BATCH_SIZE] [--epoch EPOCH]
                [--learning_rate LEARNING_RATE] [--momentum MOMENTUM]
                [--keep_prob KEEP_PROB] [--is_train IS_TRAIN]
                [--save_step SAVE_STEP] [--pred_dir_name PRED_DIR_NAME]
                [--pair_dir_name PAIR_DIR_NAME] [--crf_dir_name CRF_DIR_NAME]
                [--crf_pair_dir_name CRF_PAIR_DIR_NAME] [--width WIDTH]
                [--height HEIGHT] [--restore_target RESTORE_TARGET]

optional arguments:
  -h, --help            show this help message and exit
  --dataset DATASET     path to dataset (default:
                        ./Model/../Parser_/../Dataset)
  --set_name SET_NAME   name for set (default: val.txt)
  --label_dir_name LABEL_DIR_NAME
                        name for label directory (default: Segmentation_label)
  --img_dir_name IMG_DIR_NAME
                        name for image directory (default: JPEGImages)
  --classes CLASSES     number of classes for segmentation (default: 21)
  --batch_size BATCH_SIZE
                        batch size for training (default: 16)
  --epoch EPOCH         epoch for training (default: 2000)
  --learning_rate LEARNING_RATE
                        learning rate for training (default: 0.01)
  --momentum MOMENTUM   momentum for optimizer (default: 0.9)
  --keep_prob KEEP_PROB
                        probability for dropout (default: 0.5)
  --is_train IS_TRAIN   training or testing [1 = True / 0 = False] (default:
                        0)
  --save_step SAVE_STEP
                        step for saving weight (default: 2)
  --pred_dir_name PRED_DIR_NAME
                        name for prediction masks directory (default:
                        Pred_masks)
  --pair_dir_name PAIR_DIR_NAME
                        name for pairs directory (default: Pred_pairs)
  --crf_dir_name CRF_DIR_NAME
                        name for crf prediction masks directory (default:
                        CRF_masks)
  --crf_pair_dir_name CRF_PAIR_DIR_NAME
                        name for crf pairs directory (default: CRF_pairs)
  --width WIDTH         width for resize (default: 513)
  --height HEIGHT       height for resize (default: 513)
  --restore_target RESTORE_TARGET
                        target for restore (default: 0)

Dataset/mIoU.py

usage: mIoU.py [-h] [--dataset DATASET] [--set_name SET_NAME]
               [--GT_dir_name GT_DIR_NAME] [--Pred_dir_name PRED_DIR_NAME]
               [--classes CLASSES]

optional arguments:
  -h, --help            show this help message and exit
  --dataset DATASET     path to dataset (default:
                        ./Dataset/../Parser_/../Dataset)
  --set_name SET_NAME   name for set (default: val.txt)
  --GT_dir_name GT_DIR_NAME
                        name for ground truth directory (default:
                        SegmentationClass)
  --Pred_dir_name PRED_DIR_NAME
                        name for prediction directory (default: CRF_masks)
  --classes CLASSES     number of classes (default: 21)

Dataset/load.py

Dataset/save_result.py

Dataset/voc12_class.py

Dataset/voc12_color.py

Postprocess/dense_CRF.py

Reference