ihaeyong/pixpro-with-weights

Pixel Propagation for unsupervised visual representation learning

PixPro -- Pixel-level representation learning

Unofficial implementation of Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning.

Red and blue points show sampled locations in two image views. Large red dot marks a point in the first view and the large blue dots are "matches" for that pixel in the second view (based off a distance threshold of 0.7).

Pre-trained Weights

First run at pre-training a model is complete. Results fall short of those reported in the PixPro paper, but are on par with other unsupervised pre-training algorithms like MoCo and SimCLR.

Update: This model was trained without excluding BatchNorm parameters and biases from weight decay or LARS adaptation. This omission has been corrected; it may explain the suboptimal performance. TBD.

Download weights

Results from VOC2007-test:

pretrain	AP50	AP	AP75
ImageNet-1M, supervised	81.3	53.5	58.8
MoCo v1, 200ep	81.5	55.9	62.6
SimCLR, 1000ep	81.9	56.3	62.5
PixPro, 100ep (this repo)	81.8	56.6	63.0
PixPro, 100ep (reported)	83.0	58.8	66.5

At least some of this discrepancy may be due to differences in pre-training hyperparameters.

source	batch size	encoder momentum	epochs	number of gpus
PixPro, 100ep (this repo)	512	0.995	100	4
PixPro, 100ep (reported)	1024	0.99	100	8

The training loss had expected behavior until epoch ~80 when it starts increasing slightly.

Current Status

Implementations of the dataloader, model and train_backbone script are complete for Pixel Propagation.

• Pixel propagation module
• Suppport for all spatial transforms (crops, resizing, flips, rotations, grid/elastic deformations, etc.)
• Generic encoder and projection head for any torchvision model
• Consistency loss for pixel propagation (not pixel contrast)
• BYOL-style data augmentations
• Cosine learning rate schedule
• Momentum encoder's momentum schedule from BYOL (0.99 -> 1 during training)
• LARS optimizer
• Distributed training script for backbone network (e.g. resnet50)
• Support for mixed precision training
• Pre-trained ResNet50 backbone model
• Results on COCO and/or PASCAL

Hyperparameters and training schedules have been reproduced with as much fidelity to the original publication as possible.

If using conda, setup a new environment with required dependencies with:

conda env create -f environment.yml

Then, on an 8 GPU machine, run:

python train_backbone.py {data_directory} {save_directory} -a resnet50 -b 1024 --lr 4 \
--dist-url 'tcp://localhost:10001' --multiprocessing-distributed \
--world-size 1 --rank 0 --momentum 0.9 --fp16

Where {data_directory} should be a path to a folder containing ImageNet training data. To train with mixed precision add the --fp16 flag.

Note about smaller batch sizes

Scale the learning rate by lr = base_lr x batch_size/256 where base_lr=1. Results where not reported in the paper for smaller batch sizes; however, assuming that it behaves like the BYOL algorithm, there shouldn't be too much of a loss in performance. In addition to scaling the learning rate for smaller batches, BYOL also increases the starting momentum for the encoder. For PixPro the default momentum for a batch size of 1024 is 0.99, for a batch size of 256 it may be better to use a momentum closer to 0.995 (i.e. --pixpro-mom 0.995).