SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.01768 · 2024

SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
likyoo/SegEarth-OV canonical 4 of 9
FunctionStatusWhere it lives
convert_to_custom_text_state_dict Ran likyoo/SegEarth-OV/open_clip/model.py
pointer only (licence: NONE) · get_code("f19962ebb134b3d7")
get_cast_dtype Ran likyoo/SegEarth-OV/open_clip/model.py
pointer only (licence: NONE) · get_code("dcd422d66b0581d8")
get_cls_idx Ran likyoo/SegEarth-OV/segearth_segmentor.py
pointer only (licence: NONE) · get_code("e7ab2f08aee5f70f")
get_input_dtype Ran likyoo/SegEarth-OV/open_clip/model.py
pointer only (licence: NONE) · get_code("b476c8cfbf0f1f47")
gather_features Not yet run likyoo/SegEarth-OV/open_clip/loss.py
pointer only (licence: NONE) · get_code("ddcbd45e940484ee")
neighbour_exchange Not yet run likyoo/SegEarth-OV/open_clip/loss.py
pointer only (licence: NONE) · get_code("e332856e3c2fc814")
neighbour_exchange_bidir Not yet run likyoo/SegEarth-OV/open_clip/loss.py
pointer only (licence: NONE) · get_code("5b1fd364afcf3c05")
prepare_inputs_for_generation Not yet run likyoo/SegEarth-OV/open_clip/coca_model.py
pointer only (licence: NONE) · get_code("fb651d0a97fd4d3f")
register_pooler Not yet run likyoo/SegEarth-OV/open_clip/hf_model.py
pointer only (licence: NONE) · get_code("2a377da4a76a2d44")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Remote sensing image plays an irreplaceable role in fields such as agriculture, water resources, military, and disaster relief. Pixel-level interpretation is a critical aspect of remote sensing image applications; however, a prevalent limitation remains the need for extensive manual annotation. For this, we try to introduce open-vocabulary semantic segmentation (OVSS) into the remote sensing context. However, due to the sensitivity of remote sensing images to low-resolution features, distorted target shapes and ill-fitting boundaries are exhibited in the prediction mask. To tackle this issue, we propose a simple and general upsampler, SimFeatUp, to restore lost spatial information in deep features in a training-free style. Further, based on the observation of the abnormal response of local patch tokens to [CLS] token in CLIP, we propose to execute a straightforward subtraction operation to alleviate the global bias in patch tokens. Extensive experiments are conducted on 17 remote sensing datasets spanning semantic segmentation, building extraction, road detection, and flood detection tasks. Our method achieves an average of 5.8%, 8.2%, 4.0%, and 15.3% improvement over state-of-the-art methods on 4 tasks. All codes are released. \url{https://earth-insights.github.io/SegEarth-OV}

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.01768")
get_code_for_paper("2410.01768")
have("2410.01768")

Connect an agent — have() is free.