pith. sign in

arxiv: 2404.00701 · v1 · pith:75RCP27G · submitted 2024-03-31 · cs.CV

Training-Free Semantic Segmentation via LLM-Supervision

pith:75RCP27Gopen to challenge →

classification cs.CV
keywords segmentationsemanticmodeltext-supervisedadvancedclasscomprehensivedescriptors
0
0 comments X
read the original abstract

Recent advancements in open vocabulary models, like CLIP, have notably advanced zero-shot classification and segmentation by utilizing natural language for class-specific embeddings. However, most research has focused on improving model accuracy through prompt engineering, prompt learning, or fine-tuning with limited labeled data, thereby overlooking the importance of refining the class descriptors. This paper introduces a new approach to text-supervised semantic segmentation using supervision by a large language model (LLM) that does not require extra training. Our method starts from an LLM, like GPT-3, to generate a detailed set of subclasses for more accurate class representation. We then employ an advanced text-supervised semantic segmentation model to apply the generated subclasses as target labels, resulting in diverse segmentation results tailored to each subclass's unique characteristics. Additionally, we propose an assembly that merges the segmentation maps from the various subclass descriptors to ensure a more comprehensive representation of the different aspects in the test images. Through comprehensive experiments on three standard benchmarks, our method outperforms traditional text-supervised semantic segmentation methods by a marked margin.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference

    cs.CV 2026-05 unverdicted novelty 7.0

    VIP evolves text prompts using visual cues and saliency-aware aggregation inside dino.txt to deliver 1.4-8.4% higher mIoU on dense vision-language tasks with low overhead.

  2. VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference

    cs.CV 2026-05 unverdicted novelty 5.0

    VIP evolves text prompts via alias expansion and visual-guided distillation in dino.txt to deliver higher mIoU in dense vision-language segmentation tasks.