Add ChangeDetectionTask

[keves1]

This PR is to add a change detection trainer as mentioned in #2382.

Key points/items to discuss:

• I used the OSCD dataset to test with and modified this dataset to use a temporal dimension.
• With the added temporal dimension, Kornia’s AugmentationSequential doesn’t work, but can be combined with VideoSequential to support the temporal dimension (see Kornia docs). I overrode self.aug in the OSCDDataModule to do this but not sure if this should be incorporated into the BaseDataModule instead.
• VideoSequential adds a temporal dimension to the mask. Not sure if there is a way to avoid this, or if this is desirable, but I added an if statement to the AugmentationSequential wrapper to check for and remove this added dimension.
• The OSCDDataModule applies _RandomNCrop augmentation, but this does not work for time series data. I'm not sure how to modify _RandomNCrop to fix this and would appreciate some help/guidance.
• There are a few tests that I need to still make pass.

cc @robmarkcole

[robmarkcole]

Should go in torchgeo/losses/ ?

[keves1]

That makes sense, I'll put this and XEntJaccardLoss there.

[robmarkcole]

If stacking the channels should this be 2 * 13?

[adamjstewart]

We are no longer stacking channels, we are making all time series datasets (including change detection) into B x T x C x H x W

[robmarkcole]

OK and it is not necessary to config T?

[keves1]

in_channels is multiplied by 2 in configure_models when initializing Unet.

[robmarkcole]

and ce-jaccard ?

[keves1]

Yes, I missed that, thanks.

[robmarkcole]

Is there a paper ref for this?

[keves1]

Not that I'm aware of, and I didn't find one from a quick search. This loss function was already in there with what I started from.

[robmarkcole]

Noting that for change detection BCE may be more appropriate

#245

[robmarkcole]

I wonder if we should limit the scope to change between two timesteps and binary change - then we can use binary metrics and provide a template for the plot methods. I say this because this is the most common change detection task by a mile. Might also simplify the augmentations approach? Treating as a video sequence seems overkill.
Also I understand there is support for multitemporal coming later.

[adamjstewart]

I wonder if we should limit the scope to change between two timesteps

I'm personally okay with this, although @hfangcat has a recent work using multiple pre-event images that would be nice to support someday (could be a subclass if necessary).

and binary change

Again, this would probably be fine as a starting point, although I would someday like to make all trainers support binary/multiclass/multilabel, e.g., #2219.

provide a template for the plot methods.

Could also do this in the datasets (at least for benchmark NonGeoDatasets). We're also trying to remove explicit plotting in the trainers: #2184

I say this because this is the most common change detection task by a mile.

Agreed.

Might also simplify the augmentations approach? Treating as a video sequence seems overkill.

I actually like the video augmentations, but let me loop in the Kornia folks to get their opinion: @edgarriba @johnnv1

Also I understand there is support for multitemporal coming later.

Correct, see #2382 for the big picture (I think I also sent you a recording of my presented plan).

[adamjstewart]

VideoSequential adds a temporal dimension to the mask. Not sure if there is a way to avoid this

Can you try keepdim=True?

I added an if statement to the AugmentationSequential wrapper to check for and remove this added dimension.

@ashnair1 would this work directly with K.AugmentationSequential now? We are trying to phase out our AugmentationSequential wrapper now that upstream supports (almost?) everything we need.

[keves1]

I will go ahead and make changes for this to be for binary change and two timesteps, sounds like a good starting point.

Can you try keepdim=True?

I tried this and it didn't get rid of the other dimension. I also looked into extra_args but didn't see any options to help with this.

Could also do this in the datasets (at least for benchmark NonGeoDatasets). We're also trying to remove explicit plotting in the trainers

I was going to add plotting in the trainer, but would you rather not then? What would this look like in the dataset?

[robmarkcole]

Perhaps there should even be a base class ChangeDetection and subclasses for BinaryChangeDetection etc?

[adamjstewart]

That's exactly what I'm trying to undo in #2219.

[adamjstewart]

I was going to add plotting in the trainer, but would you rather not then?

We can copy-n-paste the validation_step plotting stuff used by other trainers, but that's probably going to disappear soon (I think we're just waiting on testing in #2184.

What would this look like in the dataset?

See OSCD.plot()