REVIEW 53 cited by
Fast Segment Anything
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
read the original abstract
The recently proposed segment anything model (SAM) has made a significant influence in many computer vision tasks. It is becoming a foundation step for many high-level tasks, like image segmentation, image caption, and image editing. However, its huge computation costs prevent it from wider applications in industry scenarios. The computation mainly comes from the Transformer architecture at high-resolution inputs. In this paper, we propose a speed-up alternative method for this fundamental task with comparable performance. By reformulating the task as segments-generation and prompting, we find that a regular CNN detector with an instance segmentation branch can also accomplish this task well. Specifically, we convert this task to the well-studied instance segmentation task and directly train the existing instance segmentation method using only 1/50 of the SA-1B dataset published by SAM authors. With our method, we achieve a comparable performance with the SAM method at 50 times higher run-time speed. We give sufficient experimental results to demonstrate its effectiveness. The codes and demos will be released at https://github.com/CASIA-IVA-Lab/FastSAM.
Forward citations
Cited by 53 Pith papers
-
GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping
GaussLite conditions 3D Gaussian Splatting seeding density, gradient flow, and scaling on task relevance masks derived from LLM-parsed natural language and open-vocabulary detection, yielding +2.72 dB ROI PSNR gains o...
-
OpenSGA: Efficient 3D Scene Graph Alignment in the Open World
OpenSGA fuses vision-language, textual, and geometric features via a distance-gated attention encoder and minimum-cost-flow allocator to outperform prior methods on both frame-to-scan and subscan-to-subscan 3D scene g...
-
LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment
LAGO achieves state-of-the-art zero-shot performance with fewer image regions by using class-agnostic object discovery followed by confidence-controlled language-guided refinement and dual-channel aggregation.
-
Seg2Change: Adapting Open-Vocabulary Semantic Segmentation Model for Remote Sensing Change Detection
Seg2Change adapts open-vocabulary segmentation models to open-vocabulary change detection via a category-agnostic change head and new dataset CA-CDD, delivering +9.52 IoU on WHU-CD and +5.50 mIoU on SECOND.
-
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wi...
-
OmniOVCD: Streamlining Open-Vocabulary Change Detection with SAM 3
OmniOVCD uses SAM 3's decoupled outputs and an SFID strategy to achieve state-of-the-art IoU scores of 67.2, 66.5, 24.5, and 27.1 on four OVCD benchmarks, surpassing prior methods.
-
TestMate: Test-Time Domain Adaptation Aided by Lightweight Vision Foundation Model
TestMate fuses FastSAM mask proposals with a segmentation network via size-ordered soft refinement to achieve backpropagation-free, first-frame TTDA gains on semantic segmentation benchmarks.
-
AtlasLC: Fast Codec-Ready Compression of Object-Centric 3D Gaussian Splatting
A training-free pipeline prunes object-centric 3D Gaussian splats by local competition and packs them into deterministic codec-ready atlases, cutting preparation time and payload with modest quality loss.
-
Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing
SegFS is a dual-path architecture that uses sparse keyframe open-vocabulary predictions to condition a fast feature-space network for efficient temporal instance segmentation in videos.
-
MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes
MV-GEL uses a learned view selector and a fine-tuned vision-language segmentation model to localize text-described faces and edges on 3D meshes.
-
MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes
MV-GEL localizes fine-grained geometric entities on 3D meshes from natural language by ranking informative views with GELviews, applying VLM segmentation, and lifting masks via geometry-aware ray casting, reporting up...
-
Rethinking Foundation Model Collaboration: Enhancing Specialized Models through Proxy Task Reasoning
FAT decomposes structured prediction into specialist hypothesis generation and foundation-model proxy reasoning, yielding consistent gains over baselines on detection, trajectory, and segmentation tasks.
-
Agentic Collaborative Cognition for Zero-Shot 3D Understanding
A closed-loop multi-agent framework with Planning and Perception agents iteratively supplements viewpoints and integrates object observations into a holistic cognitive map, achieving SOTA on six 3D benchmarks.
-
Agentic Collaborative Cognition for Zero-Shot 3D Understanding
A collaborative Planning-Perception agent framework using MLLMs constructs a holistic cognitive map through iterative viewpoint supplementation and achieves reported SOTA gains on six 3D benchmarks.
-
ReA-OVCD: Reliability-Aware Open-Vocabulary Change Detection via Semantic and Spatial Refinement
ReA-OVCD is a training-free reliability-aware method for open-vocabulary change detection that uses semantic change reasoning and boundary-aware refinement to reduce artifacts and improve accuracy on remote sensing datasets.
-
Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines
Presents MMIOC-1M benchmark with 1M+ samples across 14 super-categories and RTVPNet with domain projection, sparse sampling, and bidirectional interaction, claiming SOTA on MMIOC-1M, LVIS, and COCO.
-
Meridian: Metric-Semantic Primitive Matching for Cross-View Geo-Localization Beyond Urban Environments
Meridian matches metric-semantic primitives across aerial and ground views for training-free global localization in diverse natural environments, reporting 2.4 m average trajectory error over 19 km.
-
Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments
COTRATE is an online self-supervised framework that uses proprioceptive terrain assessment to supervise visual traversability estimation with alignment loss and diversity-aware replay for continual robot-agnostic learning.
-
Enabling Extensible Embodied Capabilities with Tools
Introduces Embodied Tool Protocol and tool externalization to improve embodied AI performance on perception and cognition tasks, with measured gains but limits on execution capabilities.
-
InstructSAM: Segment Any Instance with Any Instructions
InstructSAM uses learnable queries in a VLM to condition SAM3 for single-pass multi-instance segmentation from arbitrary instructions, with a new Inst2Seg benchmark.
-
RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation
RepSAM applies CKA-guided rank allocation in PEFT plus multi-modal fusion to adapt SAM, reaching 97.9% of full fine-tuning mIoU with 158x fewer parameters on robotic benchmarks.
-
P2DNav: Panorama-to-Downview Reasoning for Zero-shot Vision-and-Language Navigation
P2DNav proposes a three-part hierarchical framework (panorama-to-downview reasoning, sliding-window dialogue memory, and reflective reorientation) that reports large success-rate gains on the R2R-CE zero-shot VLN benchmark.
-
SparseSAM: Structured Sparsification of Activations in Segment Anything Models
SparseSAM achieves 2x faster inference and 2.8x memory reduction in SAM with only 0.004 mIoU loss at 0.4 density via Stripe-Sort Attention and Residual-Consistency MLP.
-
StateScribe: Towards Accessible Change Awareness Across Real-World Revisits
StateScribe uses a dual-layer memory architecture for episodic scenes and object-centric changes to deliver live and historical descriptions, achieving 83.1% F1 accuracy across revisits in evaluations and user studies...
-
StateScribe: Towards Accessible Change Awareness Across Real-World Revisits
StateScribe gives blind users spoken change alerts across revisits by combining episodic scene memory with object-centric temporal memory; reported F1=83.1% is inflated by duplicate-counting.
-
GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
GRAIL autonomously grounds relational concepts in NeSy-RL by using LLM weak supervision followed by interaction-based refinement, matching or exceeding manually defined concepts on Atari games.
-
H-SPAM: Hierarchical Superpixel Anything Model
H-SPAM produces accurate, regular, and perfectly nested hierarchical superpixels that outperform prior hierarchical methods and match recent non-hierarchical state-of-the-art.
-
Simulation-Driven Evolutionary Motion Parameterization for Contact-Rich Granular Scooping with a Soft Conical Robotic Hand
A deformable soft conical hand is modeled in physics simulation and its scooping trajectories are optimized via evolutionary search, enabling effective contact-rich granular tasks validated in both simulation and phys...
-
Active Semantic Perception
An LLM-based scene-graph completion routine can guide a robot to infer and find unseen rooms faster than frontier-based exploration, at least in the three simulated apartments tested.
-
AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning
AIM-CoT improves multimodal chain-of-thought by selecting image regions that reduce predictive uncertainty and inserting them when attention shifts toward the visual input.
-
AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning
AIM-CoT enhances interleaved multimodal chain-of-thought reasoning by adding context-enhanced attention generation, active visual probing via information foraging, and dynamic attention-shift triggering.
-
Terra: Hierarchical Terrain-Aware 3D Scene Graph for Task-Agnostic Outdoor Mapping
Terra produces a lightweight task-agnostic metric-semantic 3D scene graph for outdoor environments using terrain-aware place nodes and hierarchically organized regions.
-
DreamNav: A Trajectory-Based Imaginative Framework for Zero-Shot Vision-and-Language Navigation
DreamNav achieves new zero-shot SOTA on VLN-CE with an egocentric-only pipeline that generates candidate trajectories, imagines their futures, and selects the best by language alignment.
-
Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2
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.
-
MuViSeg: Multi-View Segment Correspondences from Dense Geometry Priors
A joint multi-view self-attention matcher over SAM segments beats pairwise matchers at wide baselines and lifts HM3D navigation success from 50% to 70%, while a LightGlue-style pairwise head wins outdoors and at narro...
-
HERCULES: An Open-Source Simulation Framework for Heterogeneous Multi-Robot SLAM, Collaborative Perception, and Exploration
HERCULES is a new open-source UE5-based simulator for heterogeneous multi-robot SLAM, collaborative perception, and exploration with UAV-UGV support, new controllers, LWIR sensors, and public code plus benchmark datasets.
-
Curvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubic spline arc-length integration
CucumberVision compares five 3D length methods on 48 RGB-D captures of seven cucumbers and shows a novel medial-axis cubic spline with trapezoidal integration achieves the lowest 4.13% MAPE, outperforming baselines at...
-
ESAM++: Efficient Online 3D Perception on the Edge
ESAM++ introduces a 3D Sparse Feature Pyramid Network for efficient online 3D scene perception on edge devices, claiming competitive accuracy with up to 3x faster inference and 2x smaller model size than ESAM on four ...
-
RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction
Introduces the largest global aerial road segmentation dataset and RoadGIE, an interactive model using topology-aware prompts that reports SOTA accuracy and connectivity on the new benchmark with a 3.7M parameter network.
-
TinySAM 2: Extreme Memory Compression for Efficient Track Anything Model
TinySAM 2 reaches 90% of SAM 2.1 performance on DAVIS and SA-V using 7% of the memory tokens and 3% of the training data via frame selection, spatial average pooling, temporal similarity-based token pruning, and a Rep...
-
FUS3DMaps: Scalable and Accurate Open-Vocabulary Semantic Mapping by 3D Fusion of Voxel- and Instance-Level Layers
FUS3DMaps fuses voxel- and instance-level open-vocabulary layers inside a shared 3D voxel map to improve both layers and enable scalable accurate semantic mapping.
-
A Real-time Scale-robust Network for Glottis Segmentation in Nasal Transnasal Intubation
A scale-robust lightweight CNN for glottis segmentation achieves 92.9% mDice at over 170 FPS with a 19 MB model size on three datasets.
-
Weight Group-wise Post-Training Quantization for Medical Foundation Model
Permutation-COMQ is a new post-training quantization algorithm that reorders weights within layers and uses only dot-product and rounding steps to deliver the highest reported accuracy for 2-, 4-, and 8-bit medical fo...
-
Analysis of the Dick Effect for AI-based Dynamic Gravimeter
A 0.12 s accelerometer dead time in an atom-interferometer dynamic gravimeter introduces roughly 8 mGal of measurement noise, which the paper attributes to high-frequency aliasing and analyzes with a derived frequency...
-
On Efficient Variants of Segment Anything Model: A Survey
A survey that reviews efficient variants of the Segment Anything Model, categorizes acceleration strategies, and provides a unified hardware evaluation on benchmarks.
-
Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
MobileSAM is a 60x smaller distilled version of SAM that matches original performance and runs 5x faster than concurrent FastSAM while supporting CPU inference.
-
Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation
A modular framework using FastSAM with Set-of-Mark prompting, an LLM as semantic router, and MoveIt Task Constructor achieves 62% end-to-end success in zero-shot language-guided robotic manipulation across open-world ...
-
Efficient Segment Anything with Depth-Aware Fusion and Limited Training Data
Adding monocular depth to EfficientViT-SAM improves point-prompted segmentation at 3 and 5 clicks after fine-tuning on 11.2k images, but universal gains and data-efficiency are not established.
-
SAM-MI: A Mask-Injected Framework for Enhancing Open-Vocabulary Semantic Segmentation with SAM
SAM-MI improves open-vocabulary segmentation by injecting aggregated SAM masks as low- and high-frequency guidance into CLIP cost maps, with sparse text-guided point prompts for speed.
-
Multi-modal video data-pipelines for machine learning with minimal human supervision
An open-source video pipeline automatically extracts 13+ visual modalities from raw video with no human annotation, and a sub-1M-parameter distilled model reaches near-Mask2Former accuracy on an aerial scene benchmark.
-
SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3
A frozen DINOv3 backbone plus a simple MLP head reportedly beats specialized segmentation models on six benchmarks, but the evidence lacks statistical rigor.
-
Object-Centric Cropping for Visual Few-Shot Classification
The supplied full text (arXiv:2508.00225) is a different paper from the claimed metadata (arXiv:2508.00218), so no claim about few-shot classification is backed by the manuscript.
-
Semantic-Fast-SAM: Efficient Semantic Segmenter
Semantic-Fast-SAM matches prior SAM-based semantic segmentation accuracy on Cityscapes and ADE20K while running about 20 times faster by combining FastSAM with SSA labeling and CLIP for open-vocabulary cases.
Discussion (0). Sign in to comment.