SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.11797 · 2023

CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 5 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
KU-CVLAB/CAT-Seg canonical 5 of 6
FunctionStatusWhere it lives
elu_feature_map Ran KU-CVLAB/CAT-Seg/cat_seg/modeling/transformer/model.py
code served (permissive licence) · get_code("0d5505bd782b4a89")
loadAde20K Ran KU-CVLAB/CAT-Seg/datasets/prepare_ade20k_full.py
code served (permissive licence) · get_code("6935590148878098")
window_partition Ran KU-CVLAB/CAT-Seg/cat_seg/modeling/backbone/swin.py
code served (permissive licence) · get_code("f9fd6241d935f07b")
window_partition Ran KU-CVLAB/CAT-Seg/cat_seg/modeling/transformer/model.py
code served (permissive licence) · get_code("80c66c535be6f491")
window_reverse Ran KU-CVLAB/CAT-Seg/cat_seg/modeling/backbone/swin.py
code served (permissive licence) · get_code("fb32094c6dbece71")
nested_tensor_from_tensor_list Not yet run KU-CVLAB/CAT-Seg/cat_seg/utils/misc.py
code served (permissive licence) · get_code("58cc9ff3bf75e753")

Repositories linked to this paper

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

Abstract

Open-vocabulary semantic segmentation presents the challenge of labeling each pixel within an image based on a wide range of text descriptions. In this work, we introduce a novel cost-based approach to adapt vision-language foundation models, notably CLIP, for the intricate task of semantic segmentation. Through aggregating the cosine similarity score, i.e., the cost volume between image and text embeddings, our method potently adapts CLIP for segmenting seen and unseen classes by fine-tuning its encoders, addressing the challenges faced by existing methods in handling unseen classes. Building upon this, we explore methods to effectively aggregate the cost volume considering its multi-modal nature of being established between image and text embeddings. Furthermore, we examine various methods for efficiently fine-tuning CLIP.

For agents

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

get_harvested_code_for_paper("2303.11797")
get_code_for_paper("2303.11797")
have("2303.11797")

Connect an agent — have() is free.