REVIEW 7 cited by
MobileSAMv2: Faster Segment Anything to Everything
Not yet reviewed by Pith; the record is open.
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
abstract
Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for a single object of interest, and \textbf{segment everything (SegEvery)}, which predicts the masks for all objects on the image. What makes SegAny slow for SAM is its heavyweight image encoder, which has been addressed by MobileSAM via decoupled knowledge distillation. The efficiency bottleneck of SegEvery with SAM, however, lies in its mask decoder because it needs to first generate numerous masks with redundant grid-search prompts and then perform filtering to obtain the final valid masks. We propose to improve its efficiency by directly generating the final masks with only valid prompts, which can be obtained through object discovery. Our proposed approach not only helps reduce the total time on the mask decoder by at least 16 times but also achieves superior performance. Specifically, our approach yields an average performance boost of 3.6\% (42.5\% \textit{v.s.} 38.9\%) for zero-shot object proposal on the LVIS dataset with the mask AR@$K$ metric. Qualitative results show that our approach generates fine-grained masks while avoiding over-segmenting things. This project targeting faster SegEvery than the original SAM is termed MobileSAMv2 to differentiate from MobileSAM which targets faster SegAny. Moreover, we demonstrate that our new prompt sampling is also compatible with the distilled image encoders in MobileSAM, contributing to a unified framework for efficient SegAny and SegEvery. The code is available at the same link as MobileSAM Project \href{https://github.com/ChaoningZhang/MobileSAM}{\textcolor{red}{https://github.com/ChaoningZhang/MobileSAM}}. \end{abstract}
Forward citations
Cited by 7 Pith papers
-
DL-SLAM: Enabling High-Fidelity Gaussian Splatting SLAM in Dynamic Environments based on Dual-Level Probability
Dual-level semantic-geometric dynamic probabilities let monocular Gaussian SLAM use transiently static objects for tracking yet prune them from the map, cutting ATE up to 13% and removing artifacts.
-
SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost
SAM-I2V upgrades SAM to video segmentation with three lightweight modules (temporal integrator, selective memory, memory prompts), reaching about 90% of SAM 2.1's average J&F at 0.2% of its training cost.
-
LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation
LiteMVS improves efficient multi-view stereo depth estimation by injecting semantic descriptors, MoE cost aggregation, and pseudo-labels from monocular foundation models.
-
PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation
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.
-
Compress Any Segment Anything Model (SAM)
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.
-
FastSmoothSAM: A Fast Smooth Method For Segment Anything Model
FastSmoothSAM smooths FastSAM's jagged segmentation boundaries through a four-stage B-Spline fitting pipeline, with a modest runtime overhead.
-
Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph
OVIGo-3DHSG builds a five-level scene graph (building, floor, room, location, object) and uses LLM reasoning over relevant subgraphs to ground open-vocabulary objects in multi-floor indoor scenes.
Discussion (0). Sign in to comment.