Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision
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.
Code (2)
Tasks
Exemplar-Free CountingObject CountingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Can SAM Count Anything? An Empirical Study on SAM Counting
Meta AI recently released the Segment Anything model (SAM), which has garnered attention due to its impressive performance in class-agnostic segmenting. In this study, we explore the use of SAM for the challenging task o…
Object CountingA Simple-but-effective Baseline for Training-free Class-Agnostic Counting
Class-Agnostic Counting (CAC) seeks to accurately count objects in a given image with only a few reference examples. While previous methods achieving this relied on additional training, recent efforts have shown that it'…
A Survey on Class-Agnostic Counting: Advancements from Reference-Based to Open-World Text-Guided Approaches
Object counting has recently shifted towards class-agnostic counting (CAC), which addresses the challenge of counting objects across arbitrary categories, tackling a critical need in versatile counting systems. While hum…
Object CountingA Recipe for CAC: Mosaic-based Generalized Loss for Improved Class-Agnostic Counting
Class agnostic counting (CAC) is a vision task that can be used to count the total occurrence number of any given reference objects in the query image. The task is usually formulated as a density map estimation problem t…
BenchmarkingOCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Counting
Class-Agnostic object Counting (CAC) involves counting instances of objects from arbitrary classes within an image. Due to its practical importance, CAC has received increasing attention in recent years. Most existing me…
Object Counting