A Low-Shot Object Counting Network With Iterative Prototype Adaptation
This addresses the challenge of accurately counting objects in images with limited annotations, which is important for applications like surveillance and autonomous driving, and represents a strong incremental advance over existing methods.
The paper tackled the problem of low-shot object counting in images, where only a few or no annotated exemplars are available, by introducing a new object prototype extraction module that iteratively fuses shape and appearance information. The result was a 20-30% improvement in RMSE on the FSC147 benchmark for one-shot and few-shot scenarios, achieving state-of-the-art performance.
We consider low-shot counting of arbitrary semantic categories in the image using only few annotated exemplars (few-shot) or no exemplars (no-shot). The standard few-shot pipeline follows extraction of appearance queries from exemplars and matching them with image features to infer the object counts. Existing methods extract queries by feature pooling which neglects the shape information (e.g., size and aspect) and leads to a reduced object localization accuracy and count estimates. We propose a Low-shot Object Counting network with iterative prototype Adaptation (LOCA). Our main contribution is the new object prototype extraction module, which iteratively fuses the exemplar shape and appearance information with image features. The module is easily adapted to zero-shot scenarios, enabling LOCA to cover the entire spectrum of low-shot counting problems. LOCA outperforms all recent state-of-the-art methods on FSC147 benchmark by 20-30% in RMSE on one-shot and few-shot and achieves state-of-the-art on zero-shot scenarios, while demonstrating better generalization capabilities.