Papers › FreeSeg: Free Mask from Interpretable Contrastive Language-Image Pretraining for...
FreeSeg: Free Mask from Interpretable Contrastive Language-Image Pretraining for Semantic Segmentation
Yi Li, Huifeng Yao, Hualiang Wang, Xiaomeng Li
Fully supervised semantic segmentation learns from dense masks, which requires heavy annotation cost for closed set. In this paper, we use natural language as supervision without any pixel-level annotation for open world segmentation. We call the proposed framework as FreeSeg, where the mask is freely available from raw feature map of pretraining model. Compared with zero-shot or openset segmentation, FreeSeg doesn't require any annotated masks, and it widely predicts categories beyond class-agnostic unsupervised segmentation. Specifically, FreeSeg obtains free mask from Image-Text Similarity Map (ITSM) of Interpretable Contrastive Language-Image Pretraining (ICLIP). And our core improvements are the smoothed min pooling for dense ICLIP, with the partial label and pixel strategies for segmentation. Furthermore, FreeSeg is very straight forward without complex design like grouping, clustering or retrieval. Besides the simplicity, the performances of FreeSeg surpass previous state-of-the-art at large margins, e.g. 13.4% higher at mIoU on VOC dataset in the same settings.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Zero-Shot Semantic Segmentation | COCO-Stuff | FreeSeg | Inductive Setting hIoU | - | #6 of 15 | Archive leaderboard | report |
| Zero-Shot Semantic Segmentation | COCO-Stuff | FreeSeg | Transductive Setting hIoU | 45.3 | #6 of 15 | Archive leaderboard | report |
| Zero-Shot Semantic Segmentation | PASCAL VOC | FreeSeg | Inductive Setting hIoU | - | #6 of 13 | Archive leaderboard | report |
| Zero-Shot Semantic Segmentation | PASCAL VOC | FreeSeg | Transductive Setting hIoU | 86.9 | #6 of 13 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections