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.
| Repository | Role | Ran |
|---|---|---|
| KU-CVLAB/CAT-Seg | canonical | 5 of 6 |
| Function | Status | Where 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") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
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.