# Don't waste SAM

Source: [Don't waste SAM](<https://www.sota2.com/research/paper/6a28f37590966ade919c197b>)

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

Data updated: 2026-06-11T05:00:14.404Z

Authors: Nermeen Abou Baker, Uwe Handmann

Published: 2026-06-09T10:53:33.000Z

## Abstract

Meta AI has recently released the Segment Anything Model (SAM), which demonstrates exceptional zero-shot image segmentation performance across various tasks with remarkable accuracy. Despite its inability to provide accurate segmentation across multiple research fields, SAM still serves as a valuable starting point for supporting the segmentation pipeline process, particularly for tasks that require extensive and senior skills annotations. This study aims to evaluate the generalization of SAM and fine-tuning SAM models using three waste segmentation datasets. Although they are captured from real scenes as SAM was pretrained on, these datasets present several challenges, including occlusions, deformable objects, transparency, and objects easily confused with backgrounds. In our findings, the fine-tuned SAM-ViT-H model outperforms the state-ofthe-art Zerowaste, and TACO datasets with a significant increase of +30 in IoU, and it closely approaches performance levels of TrashCan 1.0, with only a -1.44 difference. After evaluating these popular waste datasets, it became evident that fine-tuning SAM as a foundational model is a crucial step for providing better generalization for downstream waste segmentation tasks. Therefore, SAM should not be disregarded or wasted.

## 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.

- [Semantic Segmentation on ZeroWaste 5 Epochs (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-zerowaste-5-epochs-test.md>): Semantic segmentation; ZeroWaste 5 Epochs (test); mIoU: 82.79.

- [Semantic Segmentation on TACO 10 Epochs (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-taco-10-epochs-test.md>): Semantic segmentation; TACO 10 Epochs (test); mIoU: 61.06.

- [Semantic Segmentation on TrashCan 1.0 5 Epochs (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-trashcan-1-0-5-epochs-test.md>): Semantic segmentation; TrashCan 1.0 5 Epochs (test); mIoU: 78.88.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.10696>)

[PDF](<https://arxiv.org/pdf/2606.10696.pdf>)