Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision

20 May 2022  ·  Michael Hobley, Victor Prisacariu ·

Current class-agnostic counting methods can generalise to unseen classes but usually require reference images to define the type of object to be counted, as well as instance annotations during training. Reference-less class-agnostic counting is an emerging field that identifies counting as, at its core, a repetition-recognition task. Such methods facilitate counting on a changing set composition. We show that a general feature space with global context can enumerate instances in an image without a prior on the object type present. Specifically, we demonstrate that regression from vision transformer features without point-level supervision or reference images is superior to other reference-less methods and is competitive with methods that use reference images. We show this on the current standard few-shot counting dataset FSC-147. We also propose an improved dataset, FSC-133, which removes errors, ambiguities, and repeated images from FSC-147 and demonstrate similar performance on it. To the best of our knowledge, we are the first weakly-supervised reference-less class-agnostic counting method.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Object Counting FSC147 RCC MAE(val) 17.49 # 5
RMSE(val) 58.81 # 5
MAE(test) 17.12 # 6
RMSE(test) 104.53 # 6