SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.13051 · 2024

PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 9 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
xzz2/pa-sam canonical 9 of 15
FunctionStatusWhere it lives
all_gather Ran xzz2/pa-sam/utils/misc.py
pointer only (licence: NONE) · get_code("899f5dd03c569d81")
get_im_gt_name_dict Ran xzz2/pa-sam/utils/dataloader.py
pointer only (licence: NONE) · get_code("6377d2b0f1cb0b28")
get_rel_pos Ran xzz2/pa-sam/segment_anything_training/modeling/image_encoder.py
pointer only (licence: NONE) · get_code("733d7f0bedcb74c2")
get_uncertain_point_coords_with_randomness Ran xzz2/pa-sam/utils/losses.py
pointer only (licence: NONE) · get_code("752d76eca7bb4a97")
masks_to_boxes Ran xzz2/pa-sam/utils/misc.py
pointer only (licence: NONE) · get_code("cab0cc7a7011655b")
point_sample Ran xzz2/pa-sam/utils/losses.py
pointer only (licence: NONE) · get_code("965de439489202e7")
reduce_dict Ran xzz2/pa-sam/utils/misc.py
pointer only (licence: NONE) · get_code("4183d276c611a490")
window_partition Ran xzz2/pa-sam/segment_anything_training/modeling/image_encoder.py
pointer only (licence: NONE) · get_code("105fa08885dc36cc")
window_unpartition Ran xzz2/pa-sam/segment_anything_training/modeling/image_encoder.py
pointer only (licence: NONE) · get_code("50f37d517e2be27f")
build_sam_vit_b Not yet run xzz2/pa-sam/segment_anything_training/build_sam.py
pointer only (licence: NONE) · get_code("f9bc5f31ce61cee8")
build_sam_vit_h Not yet run xzz2/pa-sam/segment_anything_training/build_sam.py
pointer only (licence: NONE) · get_code("6b77c1f11fff3ed6")
build_sam_vit_l Not yet run xzz2/pa-sam/segment_anything_training/build_sam.py
pointer only (licence: NONE) · get_code("3f8890e695469246")
cat Not yet run xzz2/pa-sam/utils/losses.py
pointer only (licence: NONE) · get_code("3e4ba19cff1075ba")
create_dataloaders Not yet run xzz2/pa-sam/utils/dataloader.py
pointer only (licence: NONE) · get_code("7b785ed7aad4a361")
point_sample Not yet run xzz2/pa-sam/utils/function.py
pointer only (licence: NONE) · get_code("ab9b6bc249e53154")

Repositories linked to this paper

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

Abstract

The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially in real-world contexts. In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM. By exclusively training the prompt adapter, PA-SAM extracts detailed information from images and optimizes the mask decoder feature at both sparse and dense prompt levels, improving the segmentation performance of SAM to produce high-quality masks. Experimental results demonstrate that our PA-SAM outperforms other SAM-based methods in high-quality, zero-shot, and open-set segmentation. We're making the source code and models available at https://github.com/xzz2/pa-sam.

For agents

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

get_harvested_code_for_paper("2401.13051")
get_code_for_paper("2401.13051")
have("2401.13051")

Connect an agent — have() is free.