FocalClick-XL: Towards Unified and High-quality Interactive Segmentation

TL;DR

FocalClick-XL introduces a multi-stage, large-scale pretraining approach for interactive segmentation, enabling support for diverse interaction types and fine-grained mask predictions, achieving state-of-the-art results.

Contribution

It extends the classical FocalClick design with a novel pipeline that decomposes segmentation into meta-tasks, each pretrained independently, enhancing flexibility and performance.

Findings

State-of-the-art on click-based benchmarks

Supports diverse interaction formats including boxes and scribbles

Capable of predicting detailed alpha mattes

Abstract

Interactive segmentation enables users to extract binary masks of target objects through simple interactions such as clicks, scribbles, and boxes. However, existing methods often support only limited interaction forms and struggle to capture fine details. In this paper, we revisit the classical coarse-to-fine design of FocalClick and introduce significant extensions. Inspired by its multi-stage strategy, we propose a novel pipeline, FocalClick-XL, to address these challenges simultaneously. Following the emerging trend of large-scale pretraining, we decompose interactive segmentation into meta-tasks that capture different levels of information -- context, object, and detail -- assigning a dedicated subnet to each level.This decomposition allows each subnet to undergo scaled pretraining with independent data and supervision, maximizing its effectiveness. To enhance flexibility, we share context- and detail-level information across different interaction forms as common knowledge while introducing a prompting layer at the object level to encode specific interaction types. As a result, FocalClick-XL achieves state-of-the-art performance on click-based benchmarks and demonstrates remarkable adaptability to diverse interaction formats, including boxes, scribbles, and coarse masks. Beyond binary mask generation, it is also capable of predicting alpha mattes with fine-grained details, making it a versatile and powerful tool for interactive segmentation.