AI Paper Atlas

Research map / Detection and segmentation / CNN features

On Efficient Variants of Segment Anything Model: A Survey

Xiaorui Sun, Jun Liu, Heng Tao Shen, Xiaofeng Zhu, Ping Hu

IJCV 2025 · Detection and segmentation › CNN features · approach: Boundary-aware instance segmentation · 41 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace dense 32*32 grid prompt sampling with object-aware box prompts (YOLOv8 + NMS, max 320 prompts)MobileSAMv2 for SegEvery · SegEveryspeed: 16 times faster than the traditional 32*32 grid sampling strategyImproved
rewrite SAM with pure native PyTorch optimizationsSAM (SAMfast) · SegAnyspeed: 8x faster than the original implementationImproved
dynamic layer-wise distillation into a lightweight encoder with efficient attentionSAM-Lightening vs SAM-H · SegAnyspeed: 30× acceleration compared to SAM-HImproved
switch image encoder to Hiera and add streaming memory (SAM 2)SAM · image segmentationefficiency: 6× improvement in efficiencyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy