SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.07931 · NeurIPS · 2024

Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruning

Hong, Haofeng Liu, Erli Zhang, Junde Wu, Yueming Jin

arXiv · PDF · Open in the Atlas

Code that ran

13 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 9 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2408.07931.json · badge: /api/ran/2408.07931.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
jinlab-imvr/surgical-sam-2 canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
jinlab-imvr/Surgical-SAM-2 canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
build_sam2 Ran
ran on a synthesized input
jinlab-imvr/surgical-sam-2/sam2/build_sam.py
code served (permissive licence) · get_code("bbbfffe7be426cf5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned MockSAM2VideoPredictor. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from omegaconf import OmegaConf
import logging

torch.manual_seed(0)

# Create a minimal model class that satisfies the function's usage
class MinimalSAM2Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

# Create a minimal config class that can be instantiated
class MinimalConfig:
    def __init__(self):
        self.model = MinimalModelConfig()

class MinimalModelConfig:
    def __init__(self):
        self.sam_mask_decoder_extra_args = {}

# Mock the compose and instantiate functions from hydra
# We'll create a temporary mock setup
import sys
from unittest.mock import MagicMock

# Create mock hydra module structure
class MockHydra:
    @staticmethod
    def compose(config_name, overrides):
        cfg = OmegaConf.create({
            "model": {
                "_target_": "__main__.MinimalSAM2Model",
                "sam_mask_decoder_extra_args": {}
            }
        })
        return cfg
    
    @staticmethod
    def instantiate(cfg, _recursive_=True):
        return MinimalSAM2Model()

# Patch hydra in the function's namespace
import importlib
hydra_mock = MagicMock()
hydra_mock.compose = MockHydra.compose
hydra_mock.instantiate = MockHydra.instantiate
sys.modules['hydra'] = hydra_mock
sys.modules['hydra.utils'] = MagicMock()
sys.modules['hydra.utils'].instantiate = MockHydra.instantiate

# Create a small checkpoint file content (state dict)
model_for_ckpt = MinimalSAM2Model()
checkpoint_state_dict = model_for_ckpt.state_dict()

ARGS = {
    "config_file": "minimal_config",
    "ckpt_path": None,
    "device": "cpu",
    "mode": "eval",
    "hydra_overrides_extra": [],
    "apply_postprocessing": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
hydra, omegaconf, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockSAM2VideoPredictor — a MockSAM2VideoPredictor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockSAM2VideoPredictor output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_axial_cis Ran
ran, violated the contract we drafted
jinlab-imvr/surgical-sam-2/sam2/modeling/position_encoding.py
code served (permissive licence) · get_code("7ceaad42da42edd5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (12, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "dim": 8,
    "end_x": 4,
    "end_y": 3,
    "theta": 10000.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (12, 4) — shape (12, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
dice_loss Ran
ran; our contract draft was wrong, not the code
jinlab-imvr/surgical-sam-2/training/loss_fns.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from juneyeeHu/LM-EEC, is pointer only (licence: NONE) · get_code("e473e66fedc883c7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from juneyeeHu/LM-EEC, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_1d_sine_pe Ran
ran; our contract draft was wrong, not the code
jinlab-imvr/surgical-sam-2/sam2/modeling/sam2_utils.py
code served (permissive licence) · get_code("a6c3974188a5ffb0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# pos_inds: a 1D tensor of position indices
pos_inds = torch.arange(2, dtype=torch.int64)

# dim: embedding dimension (should be even for sine/cosine split)
dim = 4

# temperature: temperature parameter for positional encoding (default 10000)
temperature = 10000

ARGS = {
    "pos_inds": pos_inds,
    "dim": dim,
    "temperature": temperature,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_activation_fn Ran
ran; our contract draft was wrong, not the code
jinlab-imvr/surgical-sam-2/sam2/modeling/sam2_utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from CGCL-codes/UAP-SAM2, is pointer only (licence: NONE) · get_code("f2e72d81f39d65cd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from CGCL-codes/UAP-SAM2, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_per_obj_mask Ran
ran; our contract draft was wrong, not the code
jinlab-imvr/Surgical-SAM-2/tools/vos_inference.py
code served (permissive licence) · get_code("259650ecd92aae93")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small mask array with object IDs
# The mask should contain integer values where:
# - 0 represents background
# - positive integers represent different objects
mask = np.array([
    [0, 1, 1, 2],
    [0, 1, 2, 2],
    [3, 3, 0, 2],
    [3, 0, 0, 0]
], dtype=np.int32)

ARGS = {
    "mask": mask
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
init_t_xy Ran
ran, honoured the contract we drafted
jinlab-imvr/surgical-sam-2/sam2/modeling/position_encoding.py
code served (permissive licence) · get_code("bb060d29525f90eb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    'end_x': 4,
    'end_y': 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
iou_loss Ran
ran; our contract draft was wrong, not the code
jinlab-imvr/surgical-sam-2/training/loss_fns.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from juneyeeHu/LM-EEC, is pointer only (licence: NONE) · get_code("b8f501ca29e77f1a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from juneyeeHu/LM-EEC, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_ann_png Ran
ran; our contract draft was wrong, not the code
jinlab-imvr/Surgical-SAM-2/tools/vos_inference.py
code served (permissive licence) · get_code("fecc11868aafba36")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from PIL import Image
import tempfile
import os

# Create a temporary PNG file with a palette
temp_dir = tempfile.mkdtemp()
temp_path = os.path.join(temp_dir, "test_mask.png")

# Create a simple paletted image
mask_array = np.array([[0, 1, 2], [1, 2, 0]], dtype=np.uint8)
mask_img = Image.fromarray(mask_array, mode='P')

# Create and set a palette (256 colors * 3 channels for RGB)
palette = [i % 256 for i in range(768)]
mask_img.putpalette(palette)

# Save the image
mask_img.save(temp_path)

ARGS = {
    "path": temp_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
put_per_obj_mask Ran
ran, honoured the contract we drafted
jinlab-imvr/Surgical-SAM-2/tools/vos_inference.py
code served (permissive licence) · get_code("2e947f9cfdf99dc6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned ndarray, ndim 2, dtype family int, shape (4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small per_obj_mask dictionary
# The function expects a dict where keys are object_ids and values are masks
# that can be reshaped to (height, width)

height = 4
width = 3

# Create masks for 2 objects
# Each mask should be a flat array of size height*width
per_obj_mask = {
    1: np.array([1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0], dtype=np.uint8),
    2: np.array([0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1], dtype=np.uint8),
}

ARGS = {
    "per_obj_mask": per_obj_mask,
    "height": height,
    "width": width,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (4, 3) — shape (4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
reshape_for_broadcast Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jinlab-imvr/surgical-sam-2/sam2/modeling/position_encoding.py
code served (permissive licence) · get_code("f8f09f78b474ee7c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (1, 3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects:
# - freqs_cis: a 2D tensor with shape (x.shape[-2], x.shape[-1])
# - x: a tensor with ndim >= 2

# Let's create x with shape (batch, seq_len, hidden_dim) = (2, 3, 4)
# This means x.shape[-2] = 3 and x.shape[-1] = 4
x = torch.randn(2, 3, 4)

# freqs_cis should have shape (3, 4) to match (x.shape[-2], x.shape[-1])
freqs_cis = torch.randn(3, 4)

ARGS = {
    "freqs_cis": freqs_cis,
    "x": x,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (1, 3, 4) — shape (1, 3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
select_closest_cond_frames Ran
ran; our contract draft was wrong, not the code
jinlab-imvr/surgical-sam-2/sam2/modeling/sam2_utils.py
code served (permissive licence) · get_code("4ee20f090e58c425")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Construct cond_frame_outputs as a dictionary mapping frame indices to output values
# The function uses cond_frame_outputs as a dict with integer keys (frame indices)
# and arbitrary values. We'll use tensors as stand-in output values.
cond_frame_outputs = {
    0: torch.randn(2, 4),
    5: torch.randn(2, 4),
    10: torch.randn(2, 4),
    15: torch.randn(2, 4),
    20: torch.randn(2, 4),
    25: torch.randn(2, 4),
}

# frame_idx is the current frame index we're selecting conditioning frames for
frame_idx = 12

# max_cond_frame_num is the maximum number of conditioning frames to select
# Use a value that requires selection logic (not -1 and not >= len(cond_frame_outputs))
max_cond_frame_num = 3

ARGS = {
    "frame_idx": frame_idx,
    "cond_frame_outputs": cond_frame_outputs,
    "max_cond_frame_num": max_cond_frame_num,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
sigmoid_focal_loss Ran
ran; our contract draft was wrong, not the code
jinlab-imvr/surgical-sam-2/training/loss_fns.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from juneyeeHu/LM-EEC, is pointer only (licence: NONE) · get_code("42fec6fdc1faf6f1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from juneyeeHu/LM-EEC, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

build_sam2_hf Not yet run
unverified (harvested, no recorded run)
jinlab-imvr/surgical-sam-2/sam2/build_sam.py
code served (permissive licence) · get_code("b532a4eee5754aee")
How it ran

no invocation recorded.

build_sam2_video_predictor Not yet run
unverified (harvested, no recorded run)
jinlab-imvr/surgical-sam-2/sam2/build_sam.py
code served (permissive licence) · get_code("4a1bbe17897a3ec2")
How it ran

no invocation recorded.

sdp_kernel_context Not yet run
unverified (harvested, no recorded run)
jinlab-imvr/surgical-sam-2/sam2/modeling/sam/transformer.py
code served (permissive licence) · get_code("6b7c7753844ee197")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 16 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 14 the same month, 13 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
compute_axial_cis 13 other papers
2 dated earlier, 4 the same month, 7 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2306.01567 (2023-06)
Segment Anything in High Quality
2408.00874 (2024-08)
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
and 10 more not named here
init_t_xy 13 other papers
2 dated earlier, 4 the same month, 7 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2306.01567 (2023-06)
Segment Anything in High Quality
2408.00874 (2024-08)
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
and 10 more not named here
reshape_for_broadcast 13 other papers
2 dated earlier, 4 the same month, 7 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2306.01567 (2023-06)
Segment Anything in High Quality
2408.00874 (2024-08)
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
and 10 more not named here
build_sam2 10 other papers
2 dated earlier, 8 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2306.01567 (2023-06)
Segment Anything in High Quality
2410.16268 (2024-10)
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
and 7 more not named here
get_activation_fn 10 other papers
2 dated earlier, 2 the same month, 6 later
2404.07445 (2024-04)
Multi-view Aggregation Network for Dichotomous Image Segmentation
2407.10749 (2024-07)
SEED: A Simple and Effective 3D DETR in Point Clouds
2408.00874 (2024-08)
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
and 7 more not named here
get_1d_sine_pe 9 other papers
3 the same month, 6 later · 1 only as an assembly brick
2408.00714 (2024-08)
SAM 2: Segment Anything in Images and Videos
2408.00874 (2024-08)
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
2408.08870 (2024-08)
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation
and 6 more not named here
select_closest_cond_frames 9 other papers
3 the same month, 6 later · 1 only as an assembly brick
2408.00714 (2024-08)
SAM 2: Segment Anything in Images and Videos
2408.00874 (2024-08)
Medical SAM 2: Segment medical images as video via Segment Anything Model 2
2408.08870 (2024-08)
SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation
and 6 more not named here
build_sam2_video_predictor 5 other papers
1 dated earlier, 4 later
2306.01567 (2023-06)
Segment Anything in High Quality
2410.16268 (2024-10)
SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
2411.17576 (2024-11)
A Distractor-Aware Memory for Visual Object Tracking with SAM2
and 2 more not named here
dice_loss 5 other papers
1 dated earlier, 1 the same month, 3 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.00714 (2024-08)
SAM 2: Segment Anything in Images and Videos
2411.17576 (2024-11)
A Distractor-Aware Memory for Visual Object Tracking with SAM2
and 2 more not named here
iou_loss 5 other papers
1 dated earlier, 1 the same month, 3 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.00714 (2024-08)
SAM 2: Segment Anything in Images and Videos
2411.17576 (2024-11)
A Distractor-Aware Memory for Visual Object Tracking with SAM2
and 2 more not named here
sigmoid_focal_loss 5 other papers
1 dated earlier, 1 the same month, 3 later
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.00714 (2024-08)
SAM 2: Segment Anything in Images and Videos
2411.17576 (2024-11)
A Distractor-Aware Memory for Visual Object Tracking with SAM2
and 2 more not named here
build_sam2_hf 2 other papers
1 the same month, 1 later
2408.16768 (2024-08)
SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners
2501.13667 (2025-01)
MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation
get_per_obj_mask 2 other papers
1 dated earlier, 1 the same month
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.00714 (2024-08)
SAM 2: Segment Anything in Images and Videos
load_ann_png 2 other papers
1 dated earlier, 1 the same month
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.00714 (2024-08)
SAM 2: Segment Anything in Images and Videos
put_per_obj_mask 2 other papers
1 dated earlier, 1 the same month
2302.01872 (2023-02)
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
2408.00714 (2024-08)
SAM 2: Segment Anything in Images and Videos
sdp_kernel_context 2 other papers
1 the same month, 1 later · 1 only as an assembly brick
2408.00714 (2024-08)
SAM 2: Segment Anything in Images and Videos
2506.01304 (2025-06)
SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Surgical video segmentation is a critical task in computer-assisted surgery and is vital for enhancing surgical quality and patient outcomes. Recently, the Segment Anything Model 2 (SAM2) framework has shown superior advancements in image and video segmentation. However, SAM2 struggles with efficiency due to the high computational demands of processing high-resolution images and complex and long-range temporal dynamics in surgical videos. To address these challenges, we introduce Surgical SAM 2 (SurgSAM2), an advanced model to utilize SAM2 with an Efficient Frame Pruning (EFP) mechanism, to facilitate real-time surgical video segmentation. The EFP mechanism dynamically manages the memory bank by selectively retaining only the most informative frames, reducing memory usage and computational cost while maintaining high segmentation accuracy. Our extensive experiments demonstrate that SurgSAM2 significantly improves both efficiency and segmentation accuracy compared to the vanilla SAM2. Remarkably, SurgSAM2 achieves a 3× FPS compared with SAM2, while also delivering state-of-the-art performance after fine-tuning with lower-resolution data. These advancements establish SurgSAM2 as a leading model for surgical video analysis, making realtime surgical video segmentation in resource-constrained environments a reality. Our source code is available at https://github.com/jinlab-imvr/Surgical-SAM-2.

For agents

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

get_harvested_code_for_paper("2408.07931")
get_code_for_paper("2408.07931")
have("2408.07931")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.07931.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.07931.svg)](https://syntology.ai/paper/2408.07931)

Connect an agent — have() is free.