# SAM3 Self-Distillation for Fine-Grained GOOSE 2D Semantic Segmentation

arXiv: https://arxiv.org/abs/2606.20130 · HTML: https://mlsanity.com/paper/2606.20130/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 13 of its 14 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 13 of 13)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [The GOOSE Dataset for Perception in Unstructured Environments](https://mlsanity.com/paper/2310.16788/) (2023)
- [Balancing Logit Variation for Long-tailed Semantic Segmentation](https://mlsanity.com/paper/2306.02061/) (2023)
- [Excavating in the Wild: The GOOSE-Ex Dataset for Semantic Segmentation](https://mlsanity.com/paper/2409.18788/) (2024)
- [Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average](https://mlsanity.com/paper/2505.11769/) (2025)

## Abstract (arXiv)

We describe our 4th-place entry to the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which reached a composite mean Intersection-over-Union (mIoU) of 69.73% on the official 1,815-image test set. Our model adapts the image encoder of a recent visual foundation model, Segment Anything Model 3 (SAM3), with a lightweight decoder. Beyond this, we contribute two techniques and one empirical finding: (i) a self-distillation scheme that re-uses SAM3 itself, prompted with ground-truth boxes, as a teacher on the classes where it outperforms our own model; (ii) an image-level multi-scale test-time augmentation scheme that restores multi-scale inference for a fixed-input-size model by rescaling the image rather than the model input; and (iii) the finding that an aggressive photometric distortion from a winning 2025 GOOSE 2D entry, transplanted onto our pipeline, is its single largest source of improvement.