# SAMIC: Segment Anything with In-Context Spatial Prompt Engineering

Source: [SAMIC: Segment Anything with In-Context Spatial Prompt Engineering](<https://www.sota2.com/research/paper/68fa76321e209131cea6bc36>)

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

Data updated: 2025-10-26T03:48:32.506Z

Authors: Savinay Nagendra, Kashif Rashid, Chaopeng Shen, Daniel Kifer

Published: 2024-12-16T17:26:06.000Z

## Abstract

Few-shot segmentation is the problem of learning to identify specific types of objects (e.g., airplanes) in images from a small set of labeled reference images. The current state of the art is driven by resource-intensive construction of models for every new domain-specific application. Such models must be trained on enormous labeled datasets of unrelated objects (e.g., cars, trains, animals) so that their \`\`knowledge'' can be transferred to new types of objects. In this paper, we show how to leverage existing vision foundation models (VFMs) to reduce the incremental cost of creating few-shot segmentation models for new domains. Specifically, we introduce SAMIC, a small network that learns how to prompt VFMs in order to segment new types of objects in domain-specific applications. SAMIC enables any task to be approached as a few-shot learning problem. At 2.6 million parameters, it is 94% smaller than the leading models (e.g., having ResNet 101 backbone with 45+ million parameters). Even using 1/5th of the training data provided by one-shot benchmarks, SAMIC is competitive with, or sets the state of the art, on a variety of few-shot and semantic segmentation datasets including COCO-$20^i$, Pascal-$5^i$, PerSeg, FSS-1000, and NWPU VHR-10.

## 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/2412.11998>)

[PDF](<https://arxiv.org/pdf/2412.11998.pdf>)
