# Object-Centric Cropping for Visual Few-Shot Classification

Source: [Object-Centric Cropping for Visual Few-Shot Classification](<https://www.sota2.com/research/paper/68fa7a581e209131cea82a37>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:18:10.000Z

Authors: Aymane Abdali, Bartosz Boguslawski, Lucas Drumetz, Vincent Gripon

Published: 2025-07-31T23:44:06.000Z

## Abstract

In the domain of Few-Shot Image Classification, operating with as little as one example per class, the presence of image ambiguities stemming from multiple objects or complex backgrounds can significantly deteriorate performance. Our research demonstrates that incorporating additional information about the local positioning of an object within its image markedly enhances classification across established benchmarks. More importantly, we show that a significant fraction of the improvement can be achieved through the use of the Segment Anything Model, requiring only a pixel of the object of interest to be pointed out, or by employing fully unsupervised foreground object extraction methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.00218>)

[PDF](<https://arxiv.org/pdf/2508.00218.pdf>)