Suitable model for regression on thermal images

by hash_ir   Last Updated October 09, 2019 14:19 PM

I have a dataset of thermal images resulting from an experiment. Each experiment has 200 images which are in sequence. The images are 16-bit b&w cropped to the ROI. There are some parameters used for the experiment e.g. power levels and phase. I want to construct a model which takes in these sequences of images and outputs the correspoding parameters (8 in total) for the sequence i.e regression.

So far, I have tried MLP and CNN with a regression output. These two approaches have been without any temporal context. In another approach, I constructed a ConvLSTM, with a normal convolution head without temporal information followed by an LSTMCell with a regression layer. The loss landscape is better with this approach, but I am not really sure if it is an optimal solution. I also came across the TimeDistributed wrapper layer of Keras which can provide temporal information in Linear and Convolution layers.

Contextually speaking, the temporal information is very crucial in my case. I want to know whether I am in the right direction with using something like a ConvLSTM+Regression or TimeDistributed layers.

Some information about the setup I am using for training:

  • PyTorch/Keras
  • Input size: (experiments_count, time_steps, width, height, 1) normalized to 0-1 For my case, experiments_count=1000 and time_steps=200
  • Output size: (experiments_count, 8)
  • Loss function: Mean Squared Error/Mean Absolute Error
  • Optimizer: Adam
  • Batch size: 1 since the experiments count is close to 1000 and each image is 300x300

Related Questions

Updated June 20, 2016 08:08 AM

Updated March 08, 2019 21:19 PM

Updated April 06, 2017 15:19 PM

Updated April 18, 2017 19:19 PM