SparseSAM: Structured Sparsification of Activations in Segment Anything Models

• URL: http://arxiv.org/abs/2605.17633v1
• Date: Sun, 17 May 2026 19:54:22 GMT
• Title: SparseSAM: Structured Sparsification of Activations in Segment Anything Models
• Abstract summary: Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate latency inference and memory.<n>We propose SparseSAM, a training-free sparsification framework that jointly accelerates attention and layers while preserving token identity.<n>Across four segmentation benchmarks, SparseSAM loses only 0.004 mIoU at a density and 0.021 mIoU at 0.3, a 2.10x reduction in accuracy loss versus token merging advances, while achieving 2x faster inference and 2.8x memory reduction.
• Score: 26.589924688727795
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length to process, yet introduce non-trivial runtime overhead and encounter catastrophic quality drop under high compression. Other methods applying Sparse Attention focus on attention alone, leaving the MLP fully dense and capping achievable speedup. We propose SparseSAM, a (i) training-free structured sparsification framework that jointly accelerates attention and MLP layers while preserving token identity. SparseSAM introduces (ii) Stripe-Sort Attention, which uses a deterministic Z-order permutation to transform dense attention into static hardware-friendly sparse patterns, eliminating dynamic masking overhead. SparseSAM further introduces a (iii) Residual-Consistency MLP that routes only informative tokens through the MLP while propagating remaining tokens through the residual pathway. Across four segmentation benchmarks, SparseSAM loses only 0.004 mIoU at a 0.4 density and 0.021 mIoU at 0.3, a 2.10x reduction in accuracy loss versus token merging advances, while achieving 2x faster inference and 2.8x memory reduction.

Related papers

• Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models [65.49950267695267]
  We introduce Omni2LoRA, a framework for efficient parametric memory compression via coherence-preserving context distillation.<n>By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero.
  arXiv  Detail & Related papers  (2026-08-10T07:49:10Z)
• EOVSAM: Efficient Open-Vocabulary Segmentation with SAM 3 in One Pass [79.69317943751223]
  We propose an Efficient Open-Vocabulary segmentation framework with SAM 3 (EOVSAM)<n>EOVSAM adapts SAM 3 for single-pass prediction.<n>It consistently improves segmentation accuracy over vanilla SAM 3 on all evaluated datasets.
  arXiv  Detail & Related papers  (2026-08-03T14:15:37Z)
• Seeing the End at Step Zero: Accelerating Diffusion MLLMs via MLP Sparsity-Aware Truncation [6.796779304354568]
  Seer is a training-free framework that detects a valid semantic boundary at the very first denoising step through a shift in activation sparsity.<n> Experimental results demonstrate that Seer effectively eliminates padding waste, accelerating throughput by up to $sim$31$times$.
  arXiv  Detail & Related papers  (2026-07-16T04:37:02Z)
• Stage-adaptive Token Selection for Efficient Omni-modal LLMs [17.161087166882744]
  We analyze the layer-wise token dependency of om-LLMs.<n>We propose a training-free, stage-adaptive token selection method for efficient om-LLM inference.
  arXiv  Detail & Related papers  (2026-05-19T15:55:16Z)
• LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models [49.93891888238178]
  Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipeline.<n>Naive sparse attention fails on DLMs due to a KV Inflation problem, where different queries select different prefix positions.<n>We propose LOSA (Locality-aware Sparse Attention), which reuses cached prefix-attention results for stable tokens and applies sparse attention only to active tokens.
  arXiv  Detail & Related papers  (2026-04-13T20:53:51Z)
• DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention [2.7422645382944935]
  We present DyLLM, a training-free inference framework that accelerates decoding by selectively computing only salient tokens.<n>Across diverse reasoning and code-generation benchmarks, DyLLM achieves up to 9.6x higher throughput.
  arXiv  Detail & Related papers  (2026-03-09T07:02:01Z)
• StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models [57.674757786328236]
  StructSAM is a resolution-preserving merge-unmerge framework tailored to Segment Anything Model (SAM)<n>We show that StructSAM reduces encoder FLOPs by 25-30% (up to 40%+ with prompt-aware merging) with minor drops in mIoU/Dice.<n>We also provide a spectral graph coarsening view showing that score-guided merging yields bounded Laplacian spectral distortion compared to random or window-restricted baselines.
  arXiv  Detail & Related papers  (2026-03-07T18:30:58Z)
• Fast SAM2 with Text-Driven Token Pruning [52.8350457627401]
  Segment Anything Model 2 (SAM2), a vision computation model has significantly advanced in prompt-driven video object segmentation.<n>SAM2 pipelines propagate all visual tokens produced by the image encoder through downstream temporal reasoning modules, regardless of their relevance to the target object.<n>We introduce a text-guided token pruning framework that improves inference efficiency by selectively reducing token density prior to temporal propagation.
  arXiv  Detail & Related papers  (2025-12-24T18:59:05Z)
• Sequential Token Merging: Revisiting Hidden States [29.89737086314315]
  Vision Mambas (ViMs) achieve remarkable success with sub-quadratic complexity, but their efficiency remains constrained by quadratic token scaling with image resolution.<n>We propose Sequential Token Merging (STM), featuring: 1) Bidirectional nearest neighbor merging to preserve sequential dependencies through symmetric spatial aggregation, and 2) Hidden states protection to stabilize the hidden states around the class token.<n>Our method achieves state-of-the-art efficiency with minimal complexity, while providing new insights into state-space model dynamics.
  arXiv  Detail & Related papers  (2025-09-19T14:45:01Z)
• TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference [48.40143137402824]
  Multi-Head Latent Attention (MLA) compresses key-value states into a low-rank latent vector, caching only this vector to reduce memory.<n>In tensor parallelism (TP), however, attention heads are computed across multiple devices, and each device must load the full cache.<n>We propose-Parallel Latent Attention (TPLA), a scheme that partitions both the latent representation and each head's input dimension across devices, performs attention independently per shard, and then combines results with an all-reduce.
  arXiv  Detail & Related papers  (2025-08-21T15:25:40Z)
• S2-Attention: Hardware-Aware Context Sharding Among Attention Heads [49.1454481007861]
  Sparse attention selectively attends to a subset of tokens in the context.<n>It remains unclear whether sparse attention can maintain the model's quality at a scale of today's large language models.<n>This paper presents Sparsely-Sharded(S2) Attention, a Triton library that provides kernel optimization for sparse attention customizable at both per-head and per-context-range levels.
  arXiv  Detail & Related papers  (2024-07-25T00:27:07Z)
• TriMLP: Revenge of a MLP-like Architecture in Sequential Recommendation [23.32537260687907]
  We present a sequential-like architecture for sequential recommendation, namely TriMLP, with a novel Triangular Mixer for cross-token communications. In designing Triangular Mixer, we simplify the cross-token operation inascii as the basic matrix multiplication, and drop the lower-triangle neurons of the weight matrix to block the anti-chronological order connections from future tokens.
  arXiv  Detail & Related papers  (2023-05-24T03:32:31Z)
• Token Sparsification for Faster Medical Image Segmentation [37.25161294917211]
  We reformulate segmentation as a sparse encoding -> token completion -> dense decoding (SCD) pipeline. STP predicts importance scores with a lightweight sub-network and samples the topK tokens. MTA restores a full token sequence by assembling both sparse output tokens and pruned multi-layer intermediate ones.
  arXiv  Detail & Related papers  (2023-03-11T23:59:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.