Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models
About
From image-text pairs, large-scale vision-language models (VLMs) learn to implicitly associate image regions with words, which prove effective for tasks like visual question answering. However, leveraging the learned association for open-vocabulary semantic segmentation remains a challenge. In this paper, we propose a simple, yet extremely effective, training-free technique, Plug-and-Play Open-Vocabulary Semantic Segmentation (PnP-OVSS) for this task. PnP-OVSS leverages a VLM with direct text-to-image cross-attention and an image-text matching loss. To balance between over-segmentation and under-segmentation, we introduce Salience Dropout; by iteratively dropping patches that the model is most attentive to, we are able to better resolve the entire extent of the segmentation mask. PnP-OVSS does not require any neural network training and performs hyperparameter tuning without the need for any segmentation annotations, even for a validation set. PnP-OVSS demonstrates substantial improvements over comparable baselines (+26.2% mIoU on Pascal VOC, +20.5% mIoU on MS COCO, +3.1% mIoU on COCO Stuff and +3.0% mIoU on ADE20K). Our codebase is at https://github.com/letitiabanana/PnP-OVSS.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Semantic segmentation | ADE20K (val) | mIoU14.2 | 2731 | |
| Semantic segmentation | COCO Stuff (val) | mIoU17.9 | 126 | |
| Semantic segmentation | PASCAL-Context 59 class (val) | mIoU28 | 125 | |
| Semantic segmentation | COCO Object (val) | mIoU0.362 | 77 | |
| Semantic segmentation | PASCAL VOC 2012 V20 (val) | mIoU51.3 | 17 |