Papers › SAM 2: Segment Anything in Images and Videos

SAM 2: Segment Anything in Images and Videos

1 Aug 2024arXiv:2408.00714archive 2025-07-28

Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-yuan Wu, Ross Girshick, Piotr Dollár, Christoph Feichtenhofer

We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos. We build a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. Our model is a simple transformer architecture with streaming memory for real-time video processing. SAM 2 trained on our data provides strong performance across a wide range of tasks. In video segmentation, we observe better accuracy, using 3x fewer interactions than prior approaches. In image segmentation, our model is more accurate and 6x faster than the Segment Anything Model (SAM). We believe that our data, model, and insights will serve as a significant milestone for video segmentation and related perception tasks. We are releasing our main model, dataset, as well as code for model training and our demo.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 49 code samples harvested from 6 repositories linked to this paper: 40 ran (of which 9 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 0 violated, 27 with no contract checked; 11 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 11 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 5 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 44 samples from 5 repositories, 37 ran (26 with no instrument failure; 11 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 40 samples that ran have no recorded date.

facebookresearch/sam2 officialmentioned in papermentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
TripleJoy/SAM2MOT mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
bowang-lab/medsam2 mentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 12 ran (2 instrument-failed) · 3 unverified report
dcnieho/segment-anything-2 mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
facebookresearch/segment-anything mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Segment Anything (arXiv:2304.02643; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 2 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
idea-research/grounded-sam-2 mentioned on GitHubpytorchSyntology: 11 samples, 8 ran (2 instrument-failed) · 3 unverified report
louisfinner/him2sam mentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 15 ran (7 instrument-failed) · 0 unverified report
yangchris11/samurai mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory (arXiv:2411.11922; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution (arXiv:2409.12191; that paper's own run record: 12 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 4 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-7 Syntology: not harvested report
ibaiGorordo/ONNX-SAM2-Segment-Anything MITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

49 samples harvested: 40 ran (of which 9 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 0 violated, 27 with no contract checked; 11 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
11ran · our draft was wrong
27ran
9unverified

Licence: 8 of the 49 samples are pointer only, meaning Syntology does not serve that copy's text. For 8 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

facebookresearch/sam2 official repository 5 samples, 3 ran (0 instrument-failed) · 2 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
sam2/modeling/sam2_base.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d505eb599e148d6a · report fixture: returned Attention · level recorded 2026-09-22
PromptEncoder in 5 papers sam2/modeling/sam2_base.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 57e7b89d7eb0f4a7 · report fixture: returned PromptEncoder · level recorded 2026-09-22
TwoWayAttentionBlock sam2/modeling/sam2_base.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · f7f9295761cf41cf · report fixture: returned TwoWayAttentionBlock · level recorded 2026-09-22
SAM2Base sam2/modeling/sam2_base.py unverified Apache-2.0 (permissive) · e7f8982afcc2eeb8 · report
TwoWayTransformer sam2/modeling/sam2_base.py unverified Apache-2.0 (permissive) · 1337a6ec7dc01de3 · report
bowang-lab/medsam2 community (archive-listed) 15 samples, 12 ran (2 instrument-failed) · 3 unverified
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
training/loss_fns.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · e473e66fedc883c7 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_objects:int/0/int, loss_on_multimask:bool/0/bool · returned Tensor · level recorded 2026-09-25
dice_multi_class medsam2_infer_3D_CT.py ran fingerprinted Apache-2.0 (permissive) · d982bf60cc066b9a · report fixture: signature preds:ndarray/2/int, targets:ndarray/2/int · returned float64 · level recorded 2026-09-24
getLargestCC medsam2_infer_3D_CT.py ran Apache-2.0 (permissive) · 78368949ab5a1fd4 · report fixture: signature segmentation:ndarray/2/int · returned ndarray · level recorded 2026-09-24
get_center_from_recist eff_medsam2_infer_CT_lesion_npz_recist.py ran fingerprinted Apache-2.0 (permissive) · a7768a633e703a5d · report fixture: signature recist_per_lab:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_center_from_recist medsam2_infer_CT_lesion_npz_recist.py ran fingerprinted Apache-2.0 (permissive) · 11b8b72a8eb095ec · report fixture: signature recist_per_lab:ndarray/2/float, scale:int/0/int · returned ndarray · level recorded 2026-09-24
get_per_obj_mask medsam2_infer_video.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 259650ecd92aae93 · report fixture: signature mask:ndarray/2/int · returned dict · level recorded, date not recorded
iou_loss in 17 papers training/loss_fns.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · b8f501ca29e77f1a · report fixture: signature inputs:Tensor/4/float, targets:Tensor/4/float, pred_ious:Tensor/2/float, num_objects:int/0/int, loss_on_multimask:bool/0/bool, use_l1_loss:bool/0/bool · returned Tensor · level recorded 2026-09-25
load_ann_png medsam2_infer_video.py ran · our draft was wrong Apache-2.0 (permissive) · fecc11868aafba36 · report fixture: signature path:str/0/str · returned tuple · level recorded, date not recorded
put_per_obj_mask medsam2_infer_video.py ran · honoured contract Apache-2.0 (permissive) · 2e947f9cfdf99dc6 · report fixture: signature per_obj_mask:dict/0/?, height:int/0/int, width:int/0/int · returned ndarray · level recorded, date not recorded
resize_grayscale_to_rgb_and_resize eff_medsam2_infer_CT_lesion_npz_recist.py ran Apache-2.0 (permissive) · 99b787e2d3339598 · report fixture: signature array:ndarray/3/int, image_size:int/0/int · returned ndarray · level recorded 2026-09-24
sample_points_in_bbox_grid eff_medsam2_infer_CT_lesion_npz_recist.py ran Apache-2.0 (permissive) · 621ef2b926968142 · report fixture: signature bbox:ndarray/1/float, n:int/0/int · returned ndarray · level recorded 2026-09-24
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
training/loss_fns.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 42fec6fdc1faf6f1 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_objects:int/0/int, alpha:float/0/float, gamma:float/0/float, loss_on_multimask:bool/0/bool · returned Tensor · level recorded 2026-09-25
build_efficienttam efficient_track_anything/build_efficienttam.py unverified Apache-2.0 (permissive) · a66342f2959074d2 · report
build_efficienttam_hf efficient_track_anything/build_efficienttam.py unverified Apache-2.0 (permissive) · 52aac67080d89311 · report
build_efficienttam_video_predictor efficient_track_anything/build_efficienttam.py unverified Apache-2.0 (permissive) · 1191ad63c426c255 · report
dcnieho/segment-anything-2 community (archive-listed) 1 sample, 0 ran · 1 unverified
SAM2Base sam2/modeling/sam2_base.py unverified Apache-2.0 (permissive) · 784c0ac2dd86664c · report
idea-research/grounded-sam-2 community (archive-listed) 11 samples, 8 ran (2 instrument-failed) · 3 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
sam2/modeling/sam2_base.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d47d7ea80c6eb2e1 · report fixture: returned Attention · level recorded 2026-09-22
MLP in 375 papers sam2/modeling/sam2_base.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · b2caccbe8a2ad968 · report fixture: returned MLP · level recorded 2026-09-22
MaskDecoder in 7 papers sam2/modeling/sam2_base.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2ec3b3adb254bc95 · report fixture: returned MaskDecoder · level recorded 2026-09-22
PositionEmbeddingRandom in 8 papers sam2/modeling/sam2_base.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2d44a88dd1788d01 · report fixture: returned PositionEmbeddingRandom · level recorded 2026-09-22
PromptEncoder in 5 papers sam2/modeling/sam2_base.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 0d0005d3af5adb47 · report fixture: returned PromptEncoder · level recorded 2026-09-22
TwoWayAttentionBlock sam2/modeling/sam2_base.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · ea24008f11c4c7ec · report fixture: returned TwoWayAttentionBlock · level recorded 2026-09-22
get_1d_sine_pe in 9 papers sam2/modeling/sam2_base.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a6c3974188a5ffb0 · report fixture: signature pos_inds:Tensor/1/int, dim:int/0/int, temperature:int/0/int · returned Tensor · level recorded 2026-09-22
select_closest_cond_frames in 9 papers sam2/modeling/sam2_base.py ran · our draft was wrong Apache-2.0 (permissive) · 4ee20f090e58c425 · report fixture: signature frame_idx:int/0/int, cond_frame_outputs:dict/0/?, max_cond_frame_num:int/0/int · returned tuple · level recorded 2026-09-22
SAM2Base sam2/modeling/sam2_base.py unverified Apache-2.0 (permissive) · 21359b77bae173ac · report
TwoWayTransformer sam2/modeling/sam2_base.py unverified Apache-2.0 (permissive) · 9a8c4da19cecdb81 · report
sdp_kernel_context sam2/modeling/sam2_base.py unverified Apache-2.0 (permissive) · d5eb78117313126d · report
louisfinner/him2sam community (archive-listed) 15 samples, 15 ran (7 instrument-failed) · 0 unverified
adjust_keep_rate in 11 papers lib/utils/ce_utils.py ran Apache-2.0 (permissive) · 305742bafecf04f8 · report fixture: signature epoch:int/0/int, warmup_epochs:int/0/int, total_epochs:int/0/int, ITERS_PER_EPOCH:int/0/int, base_keep_rate:float/0/float, max_keep_rate:float/0/float, iters:int/0/int · returned float · level recorded 2026-09-24
all_gather in 119 papers lib/utils/misc.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · aa6da43d05cfaf65 · report fixture: signature data:dict/0/? · returned list · level recorded 2026-09-24
box_cxcywh_to_xyxy in 60 papers lib/utils/box_ops.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · e0a06ded5d4f6c3c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
box_xywh_to_xyxy in 10 papers lib/utils/box_ops.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 40c655a7fe309e49 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
box_xyxy_to_xywh in 19 papers lib/utils/box_ops.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b48a27604b9574e0 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
collate_fn in 500 papers lib/utils/misc.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 3f82133185c8bcb4 · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
compute_grids in 7 papers lib/utils/heapmap_utils.py ran · our draft was wrong Apache-2.0 (permissive) · f0de0cc660ea9823 · report fixture: signature features:list/1/Tensor, strides:list/1/int · returned list · level recorded 2026-09-24
generate_bbox_mask in 7 papers lib/utils/ce_utils.py ran fingerprinted Apache-2.0 (permissive) · d8da96a9ed23308f · report fixture: signature bbox_mask:Tensor/3/float, bbox:Tensor/2/float · returned Tensor · level recorded 2026-09-24
generate_heatmap in 9 papers lib/utils/heapmap_utils.py ran Apache-2.0 (permissive) · 02f602286c531143 · report fixture: signature bboxes:Tensor/3/float, patch_size:int/0/int, stride:int/0/int · returned list · level recorded 2026-09-24
generate_mask_cond in 7 papers lib/utils/ce_utils.py ran Apache-2.0 (permissive) · 90e571943800f79c · report fixture: signature cfg:MockConfig/0/?, bs:int/0/int, device:device/0/?, gt_bbox:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_center3x3 in 6 papers lib/utils/heapmap_utils.py ran Apache-2.0 (permissive) · 8ed1a71ee932713a · report fixture: signature locations:Tensor/2/float, centers:Tensor/2/float, strides:Tensor/1/float, range:int/0/int · returned Tensor · level recorded 2026-09-24
get_qkv in 6 papers lib/utils/merge.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 2e6c35cccbde1c71 · report fixture: signature inp_list:list/1/dict · returned tuple · level recorded 2026-09-24
merge_template_search in 6 papers lib/utils/merge.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · c66db0b9eb9bb36a · report fixture: signature inp_list:list/1/dict, return_search:bool/0/bool, return_template:bool/0/bool · returned dict · level recorded 2026-09-24
reduce_dict in 73 papers lib/utils/misc.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 05992505df9ef0cd · report fixture: signature input_dict:dict/0/?, average:bool/0/bool · returned dict · level recorded 2026-09-24
slt_collate lib/train/train_script.py ran Apache-2.0 (permissive) · 954460c5c93e5dfe · report fixture: signature batch:list/1/dict · returned dict · level recorded 2026-09-24
ibaiGorordo/ONNX-SAM2-Segment-Anything community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
draw_mask in 6 papers sam2/utils.py ran MIT (permissive) · 8922173c3fa12488 · report fixture: signature image:ndarray/3/int, mask:ndarray/2/int, color:tuple/1/int, alpha:float/0/float, draw_border:bool/0/bool · returned ndarray · level recorded 2026-09-24
draw_masks sam2/utils.py ran MIT (permissive) · 23e01949c7f7b63f · report fixture: signature image:ndarray/3/int, masks:dict/0/?, alpha:float/0/float, draw_border:bool/0/bool · returned ndarray · level recorded 2026-09-24

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for SAM 2 (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for SAM 2 (graph method: SAM 2). 12 bricks; individually on a fixture: 9 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SAM2Base entry · level 0 · unverified · 21359b77bae173ac
  2. MLP helper · level 1 · ran · b2caccbe8a2ad968
  3. MaskDecoder helper · level 1 · ran · 2ec3b3adb254bc95
  4. PromptEncoder helper · level 1 · ran · 0d0005d3af5adb47
  5. TwoWayTransformer helper · level 0 · unverified · 9a8c4da19cecdb81
  6. get_1d_sine_pe helper · level 1 · ran · our draft was wrong · a6c3974188a5ffb0
  7. select_closest_cond_frames helper · level 1 · ran · our draft was wrong · 4ee20f090e58c425
  8. LayerNorm2d helper · level 1 · ran · b44d2d4c43f5956f
  9. PositionEmbeddingRandom helper · level 1 · ran · 2d44a88dd1788d01
  10. Attention helper · level 1 · ran · d47d7ea80c6eb2e1
  11. TwoWayAttentionBlock helper · level 1 · ran · ea24008f11c4c7ec
  12. sdp_kernel_context helper · level 0 · unverified · d5eb78117313126d

harvested Assembly for SAM 2 (graph method: SAM 2). 11 bricks; individually on a fixture: 9 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SAM2Base entry · level 0 · unverified · e7f8982afcc2eeb8
  2. MLP helper · level 1 · ran · b2caccbe8a2ad968
  3. MaskDecoder helper · level 1 · ran · 2ec3b3adb254bc95
  4. PromptEncoder helper · level 1 · ran · 57e7b89d7eb0f4a7
  5. TwoWayTransformer helper · level 0 · unverified · 1337a6ec7dc01de3
  6. get_1d_sine_pe helper · level 1 · ran · our draft was wrong · a6c3974188a5ffb0
  7. select_closest_cond_frames helper · level 1 · ran · our draft was wrong · 4ee20f090e58c425
  8. LayerNorm2d helper · level 1 · ran · b44d2d4c43f5956f
  9. PositionEmbeddingRandom helper · level 1 · ran · 2d44a88dd1788d01
  10. Attention helper · level 1 · ran · d505eb599e148d6a
  11. TwoWayAttentionBlock helper · level 1 · ran · f7f9295761cf41cf

harvested Assembly for SAM 2 (graph method: SAM 2). 11 bricks; individually on a fixture: 9 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. SAM2Base entry · level 0 · unverified · 784c0ac2dd86664c
  2. MLP helper · level 1 · ran · b2caccbe8a2ad968
  3. MaskDecoder helper · level 1 · ran · 2ec3b3adb254bc95
  4. PromptEncoder helper · level 1 · ran · 57e7b89d7eb0f4a7
  5. TwoWayTransformer helper · level 0 · unverified · 1337a6ec7dc01de3
  6. get_1d_sine_pe helper · level 1 · ran · our draft was wrong · a6c3974188a5ffb0
  7. select_closest_cond_frames helper · level 1 · ran · our draft was wrong · 4ee20f090e58c425
  8. LayerNorm2d helper · level 1 · ran · b44d2d4c43f5956f
  9. PositionEmbeddingRandom helper · level 1 · ran · 2d44a88dd1788d01
  10. Attention helper · level 1 · ran · d505eb599e148d6a
  11. TwoWayAttentionBlock helper · level 1 · ran · f7f9295761cf41cf

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2408.00714") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image SegmentationRobot Manipulation GeneralizationSegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo SegmentationVideo Semantic SegmentationVisual Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) SAM2 J&F 90.7 #1 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) SAM2 Params(M) 224.4 #1 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation MOSE SAM2 J&F 77.9 #1 of 17 Archive leaderboard report
Video Object Segmentation M$^3$-VOS SAM 2 Average IOU 69.5 #4 of 4 Archive leaderboard report
Visual Object Tracking DiDi SAM2.1 Tracking quality 0.649 #3 of 11 Archive leaderboard report
Visual Object Tracking VOT2022 SAM2.1 EAO 0.692 #2 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SAM

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections