Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: De Marinis, Pasquale, Fanelli, Nicola, Scaringi, Raffaele, Colonna, Emanuele, Fiameni, Giuseppe, Vessio, Gennaro, Castellano, Giovanna
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915455234473984
author De Marinis, Pasquale
Fanelli, Nicola
Scaringi, Raffaele
Colonna, Emanuele
Fiameni, Giuseppe
Vessio, Gennaro
Castellano, Giovanna
author_facet De Marinis, Pasquale
Fanelli, Nicola
Scaringi, Raffaele
Colonna, Emanuele
Fiameni, Giuseppe
Vessio, Gennaro
Castellano, Giovanna
contents Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a novel transformer-based architecture designed for multi-prompt, multi-way few-shot semantic segmentation. Our approach leverages diverse visual prompts -- points, bounding boxes, and masks -- to create a highly flexible and generalizable framework that significantly reduces annotation burden while maintaining high accuracy. Label Anything makes three key contributions: ($\textit{i}$) we introduce a new task formulation that relaxes conventional few-shot segmentation constraints by supporting various types of prompts, multi-class classification, and enabling multiple prompts within a single image; ($\textit{ii}$) we propose a novel architecture based on transformers and attention mechanisms; and ($\textit{iii}$) we design a versatile training procedure allowing our model to operate seamlessly across different $N$-way $K$-shot and prompt-type configurations with a single trained model. Our extensive experimental evaluation on the widely used COCO-$20^i$ benchmark demonstrates that Label Anything achieves state-of-the-art performance among existing multi-way few-shot segmentation methods, while significantly outperforming leading single-class models when evaluated in multi-class settings. Code and trained models are available at https://github.com/pasqualedem/LabelAnything.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02075
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts
De Marinis, Pasquale
Fanelli, Nicola
Scaringi, Raffaele
Colonna, Emanuele
Fiameni, Giuseppe
Vessio, Gennaro
Castellano, Giovanna
Computer Vision and Pattern Recognition
Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a novel transformer-based architecture designed for multi-prompt, multi-way few-shot semantic segmentation. Our approach leverages diverse visual prompts -- points, bounding boxes, and masks -- to create a highly flexible and generalizable framework that significantly reduces annotation burden while maintaining high accuracy. Label Anything makes three key contributions: ($\textit{i}$) we introduce a new task formulation that relaxes conventional few-shot segmentation constraints by supporting various types of prompts, multi-class classification, and enabling multiple prompts within a single image; ($\textit{ii}$) we propose a novel architecture based on transformers and attention mechanisms; and ($\textit{iii}$) we design a versatile training procedure allowing our model to operate seamlessly across different $N$-way $K$-shot and prompt-type configurations with a single trained model. Our extensive experimental evaluation on the widely used COCO-$20^i$ benchmark demonstrates that Label Anything achieves state-of-the-art performance among existing multi-way few-shot segmentation methods, while significantly outperforming leading single-class models when evaluated in multi-class settings. Code and trained models are available at https://github.com/pasqualedem/LabelAnything.
title Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.02075