---
title: "Semantic Segmentation"
description: "1 posts about Semantic Segmentation, summarised, each linking to the original."
---

# Semantic Segmentation
> 1 posts about Semantic Segmentation, summarised, each linking to the original.

## Articles

### [Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation](https://yomu.fyi/post/pixels-to-tokens-token-space-efficient-active-learning-for-low-budget.md)
- Company: [Apple](https://yomu.fyi/company/apple.md)
- Published: Oct 21, 2026
- Type: Problem & solution

Current active learning strategies for vision transformers in semantic segmentation require extensive pixel labeling, impractical when only one pixel per image is labeled. TEAL is the first pixel-level active learning framework built around ViT representations, using a frozen backbone and diversity-based selection directly on the native token lattice to avoid interpolation artifacts. It applies a two-level MaxHerding strategy over multi-layer token descriptors for representative candidate selection, followed by margin-based uncertainty refinement on a decoder grid. Across CamVid, Cityscapes, ADE20K, and Pascal Context, TEAL improves over the strongest baseline by up to +24.36 mIoU with a single labeled pixel per image and reaches 97% of fully supervised performance with just 10 pixels. The improvements persist when all baselines use the same DINOv3 backbone, showing that token-space selection with decoder-grid refinement makes ViT token geometry effective for low-budget active segmentation.
