Papers › EdgeTAM: On-Device Track Anything Model

EdgeTAM: On-Device Track Anything Model

13 Jan 2025CVPR 2025 1arXiv:2501.07256archive 2025-07-28

Chong Zhou, Chenchen Zhu, Yunyang Xiong, Saksham Suri, Fanyi Xiao, Lemeng Wu, Raghuraman Krishnamoorthi, Bo Dai, Chen Change Loy, Vikas Chandra, Bilge Soran

On top of Segment Anything Model (SAM), SAM 2 further extends its capability from image to video inputs through a memory bank mechanism and obtains a remarkable performance compared with previous methods, making it a foundation model for video segmentation task. In this paper, we aim at making SAM 2 much more efficient so that it even runs on mobile devices while maintaining a comparable performance. Despite several works optimizing SAM for better efficiency, we find they are not sufficient for SAM 2 because they all focus on compressing the image encoder, while our benchmark shows that the newly introduced memory attention blocks are also the latency bottleneck. Given this observation, we propose EdgeTAM, which leverages a novel 2D Spatial Perceiver to reduce the computational cost. In particular, the proposed 2D Spatial Perceiver encodes the densely stored frame-level memories with a lightweight Transformer that contains a fixed set of learnable queries. Given that video segmentation is a dense prediction task, we find preserving the spatial structure of the memories is essential so that the queries are split into global-level and patch-level groups. We also propose a distillation pipeline that further improves the performance without inference overhead. As a result, EdgeTAM achieves 87.7, 70.0, 72.3, and 71.7 J&F on DAVIS 2017, MOSE, SA-V val, and SA-V test, while running at 16 FPS on iPhone 15 Pro Max.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2501.07256")

Code

Syntology Ran 7 of 8 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: found in paper text by Syntology: 8 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/edgetam officialmentioned in papermentioned on GitHubpytorch 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.

Code Syntology ran Syntology

8 samples harvested; 7 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
2ran
1unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from facebookresearch/sam2. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

Attention facebookresearch/sam2/sam2/modeling/memory_attention.py found in paper text by Syntology ran Apache-2.0 (permissive) · c140570681a00c3c · report
RoPEAttention facebookresearch/sam2/sam2/modeling/memory_attention.py found in paper text by Syntology ran Apache-2.0 (permissive) · 4f347f5c9d9e7597 · report
apply_rotary_enc facebookresearch/sam2/sam2/modeling/memory_attention.py found in paper text by Syntology ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 844d836b99dc1aa7 · report
compute_axial_cis facebookresearch/sam2/sam2/modeling/memory_attention.py found in paper text by Syntology ran · violated contract Apache-2.0 (permissive) · 7ceaad42da42edd5 · report
get_clones facebookresearch/sam2/sam2/modeling/memory_attention.py found in paper text by Syntology ran · our draft was wrong Apache-2.0 (permissive) · 3ef3feb872840557 · report
init_t_xy facebookresearch/sam2/sam2/modeling/memory_attention.py found in paper text by Syntology ran · honoured contract fingerprinted Apache-2.0 (permissive) · bb060d29525f90eb · report
reshape_for_broadcast facebookresearch/sam2/sam2/modeling/memory_attention.py found in paper text by Syntology ran · fixture could not drive it Apache-2.0 (permissive) · f8f09f78b474ee7c · report
MemoryAttention facebookresearch/sam2/sam2/modeling/memory_attention.py found in paper text by Syntology unverified Apache-2.0 (permissive) · dcd56b84a90a2922 · report

Tasks

Video SegmentationVideo Semantic Segmentationmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutFocusLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSAMSETSoftmaxTransformer

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