CALICO: Part-Focused Semantic Co-Segmentation with Large Vision-Language Models

TL;DR

This paper introduces CALICO, a vision-language model designed for part-focused semantic co-segmentation across multiple images, enabling detailed object part reasoning with minimal parameter tuning.

Contribution

CALICO is the first LVLM tailored for multi-image part-level reasoning, featuring novel modules for semantic correspondence extraction and adaptation.

Findings

CALICO achieves strong performance on the MixedParts dataset.

It requires only 0.3% of parameters to be finetuned.

The model effectively identifies common and unique object parts across images.

Abstract

Recent advances in Large Vision-Language Models (LVLMs) have enabled general-purpose vision tasks through visual instruction tuning. While existing LVLMs can generate segmentation masks from text prompts for single images, they struggle with segmentation-grounded reasoning across images, especially at finer granularities such as object parts. In this paper, we introduce the new task of part-focused semantic co-segmentation, which involves identifying and segmenting common objects, as well as common and unique object parts across images. To address this task, we present CALICO, the first LVLM designed for multi-image part-level reasoning segmentation. CALICO features two key components, a novel Correspondence Extraction Module that identifies semantic part-level correspondences, and Correspondence Adaptation Modules that embed this information into the LVLM to facilitate multi-image understanding in a parameter-efficient manner. To support training and evaluation, we curate MixedParts, a large-scale multi-image segmentation dataset containing $\sim$2.4M samples across $\sim$44K images spanning diverse object and part categories. Experimental results demonstrate that CALICO, with just 0.3% of its parameters finetuned, achieves strong performance on this challenging task.