Pith. sign in

REVIEW 5 cited by

EdgeSAM: Prompt-In-the-Loop Distillation for SAM

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.06660 v3 pith:Y4LSEROF submitted 2023-12-11 cs.CV

Chong Zhou , Xiangtai Li , Chen Change Loy , Bo Dai This is my paper
classification cs.CV
keywords distillationedgesamencoderdevicesedgecapturemaskmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents EdgeSAM, an accelerated variant of the Segment Anything Model (SAM), optimized for efficient execution on edge devices with minimal compromise in performance. Our approach involves distilling the original ViT-based SAM image encoder into a purely CNN-based architecture, better suited for edge devices. We carefully benchmark various distillation strategies and demonstrate that task-agnostic encoder distillation fails to capture the full knowledge embodied in SAM. To overcome this bottleneck, we include both the prompt encoder and mask decoder in the distillation process, with box and point prompts in the loop, so that the distilled model can accurately capture the intricate dynamics between user input and mask generation. To mitigate dataset bias issues stemming from point prompt distillation, we incorporate a lightweight module within the encoder. As a result, EdgeSAM achieves a 37-fold speed increase compared to the original SAM, and it also outperforms MobileSAM/EfficientSAM, being over 7 times as fast when deployed on edge devices while enhancing the mIoUs on COCO and LVIS by 2.3/1.5 and 3.1/1.6, respectively. It is also the first SAM variant that can run at over 30 FPS on an iPhone 14. Code and demo are available at https://www.mmlab-ntu.com/project/edgesam.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation

    cs.CV 2025-06 conditional novelty 7.0 of 10

    A point-prompted segmentation model gains efficiency by foveated tokenization, cutting tokens from 4096 to 172 while staying competitive on mIoU benchmarks.

  2. Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Lean-SAM2 combines target-anchored memory pruning, condensed insurance memory, and risk-aware window routing to accelerate SAM2.1 inference ~1.4× with better accuracy than Efficient-SAM2.

  3. PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation

    cs.CV 2026-03 conditional novelty 5.0 of 10

    A 1.3M-parameter CNN with ROI-implicit prompting and SAM3 distillation reaches ~65% mIoU on COCO/LVIS and 11.82 ms INT8 inference fully in-sensor on the Sony IMX500.

  4. Compress Any Segment Anything Model (SAM)

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Birkhoff compresses 18 SAM variants to about one-fifth their size with less than 1% accuracy loss, data-free, using a trajectory-based codebook and a fused GPU operator.

  5. Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges

    cs.CV 2025-07 conditional novelty 2.0 of 10

    A structured survey of prompt engineering methods for the Segment Anything Model, covering geometric, textual, and multimodal prompts and their applications.

Pith tools