I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation

• URL: http://arxiv.org/abs/2509.10334v1
• Date: Fri, 12 Sep 2025 15:14:19 GMT
• Title: I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation
• Abstract summary: Quantization offers an effective strategy to improve efficiency, but ViT-based segmentation models are notoriously fragile under low precision.<n>We introduce I-Segmenter, the first fully integer-only ViT segmentation framework.<n>I-Segmenter achieves competitive accuracy even in one-shot PTQ with a single calibration image.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, yet their deployment on resource-constrained devices remains limited due to their high memory footprint and computational cost. Quantization offers an effective strategy to improve efficiency, but ViT-based segmentation models are notoriously fragile under low precision, as quantization errors accumulate across deep encoder-decoder pipelines. We introduce I-Segmenter, the first fully integer-only ViT segmentation framework. Building on the Segmenter architecture, I-Segmenter systematically replaces floating-point operations with integer-only counterparts. To further stabilize both training and inference, we propose $\lambda$-ShiftGELU, a novel activation function that mitigates the limitations of uniform quantization in handling long-tailed activation distributions. In addition, we remove the L2 normalization layer and replace bilinear interpolation in the decoder with nearest neighbor upsampling, ensuring integer-only execution throughout the computational graph. Extensive experiments show that I-Segmenter achieves accuracy within a reasonable margin of its FP32 baseline (5.1 % on average), while reducing model size by up to 3.8x and enabling up to 1.2x faster inference with optimized runtimes. Notably, even in one-shot PTQ with a single calibration image, I-Segmenter delivers competitive accuracy, underscoring its practicality for real-world deployment.

Related papers

• Enabling Fully Integer-Only Inference for Lightweight Detection Transformers [0.19116784879310025]
  Key components, including deformable attention, feature fusion, and nonlinear activation functions, are not compatible with integer arithmetic.<n>We develop I-LW-DETR, the first fully integer-only lightweight DETR.<n>I-LW-DETR is built upon three key components: a scale-preserving split convolution that assigns independent activation scale to each branch of the multi-scale projector; SD-ShiftGELU, a sign-dependent GELU approximation that preserves element-wise behavior while avoiding the accuracy degradation; and a constrained Shiftmax that maintains stable Softmax normalization.
  arXiv  Detail & Related papers  (2026-07-27T18:33:18Z)
• Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders [123.58723804218151]
  Vision foundation models are bottlenecked by the quadratic cost of self-attention.<n>We present C-GSPN based on 2D spatial propagation propagation.
  arXiv  Detail & Related papers  (2026-05-30T14:29:43Z)
• Evolving Layer-Specific Scalar Functions for Hardware-Aware Transformer Adaptation [0.5266471639657487]
  Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is hindered.<n>Recent methods attempt to bypass this by replacing normalization layers with hardware-friendly scalar approximations.<n>We propose a highly efficient framework that utilizes genetic programming (GP) to evolve heterogeneous, layer-specific scalar functions.
  arXiv  Detail & Related papers  (2026-05-13T19:08:55Z)
• Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs [34.72414661826396]
  We present Bit-by-Bit, a progressive QAT framework with outlier channel splitting.<n>Our approach integrates three key components: (1) block-wise progressive training that reduces precision stage by stage; (2) nested structure of integer quantization grids; and (3) rounding-aware outlier channel splitting.<n>Under W2A2 settings, Bit-by-Bit significantly outperforms baselines like BitDistiller and EfficientQAT on both Llama2/3, achieving a loss of only 2.25 WikiText2 PPL compared to full-precision models.
  arXiv  Detail & Related papers  (2026-04-09T06:56:39Z)
• BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design [71.97035034203275]
  We analyze zero-point distortion in binarization and propose a Binary Weights & Ternary Activations (BWTA) quantization scheme.<n>For training, we propose Smooth Multi-Stage Quantization, combining a Levelwise Degradation Strategy and a MagnitudeAlignment Projection Factor.<n>Experiments show that BWTA approaches full-precision performance for Transformer-based models, with an average 3.5% drop on GLUE and less than 2% drop on five tasks.
  arXiv  Detail & Related papers  (2026-04-05T04:25:07Z)
• 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)
• Binary-Gaussian: Compact and Progressive Representation for 3D Gaussian Segmentation [83.90109373769614]
  3D Gaussian Splatting (3D-GS) has emerged as an efficient 3D representation and a promising foundation for semantic tasks like segmentation.<n>We propose a coarse-to-fine binary encoding scheme for per-Gaussian category representation, which compresses each feature into a single integer via the binary-to-decimal mapping.<n>We further design a progressive training strategy that decomposes panoptic segmentation into a series of independent sub-tasks, reducing inter-class conflicts and thereby enhancing fine-grained segmentation capability.
  arXiv  Detail & Related papers  (2025-11-30T15:51:30Z)
• GSPN-2: Efficient Parallel Sequence Modeling [101.33780567131716]
  Generalized Spatial Propagation Network (GSPN) addresses this by replacing quadratic self-attention with a line-scan propagation scheme.<n>GSPN-2 establishes a new efficiency frontier for modeling global spatial context in vision applications.
  arXiv  Detail & Related papers  (2025-11-28T07:26:45Z)
• Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing [8.705453442427585]
  Large language models (LLMs) have achieved near-human performance across diverse reasoning tasks.<n>Their deployment on resource-constrained Internet-of-Things (IoT) devices remains impractical due to massive parameter footprints and memory-intensive autoregressive decoding.<n>This work introduces the first autoregressive-aware split computing framework designed explicitly for LLM deployment on edge devices.
  arXiv  Detail & Related papers  (2025-11-06T02:55:07Z)
• MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning [91.90342432541138]
  Scaling up model size and training data has advanced foundation models for instance-level perception.<n>High computational cost limits adoption on resource-constrained platforms.<n>We introduce a new benchmark for efficient segmentation on both high-performance computing platforms and mobile devices.
  arXiv  Detail & Related papers  (2025-10-16T18:00:00Z)
• An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentation [5.6873464177873245]
  This paper introduces an efficient dual-line decoder segmentation network (EDLDNet)<n>The proposed method features a noisy decoder, which learns to incorporate structured perturbation at training time for better model robustness.<n>By leveraging multi-scale segmentation masks from both decoders, we also utilize a mutation-based loss function to enhance the model's generalization.
  arXiv  Detail & Related papers  (2025-08-23T12:34:27Z)
• FA-Seg: A Fast and Accurate Diffusion-Based Method for Open-Vocabulary Segmentation [1.4525238046020867]
  Open-vocabulary semantic segmentation aims to segment objects from arbitrary text categories without requiring densely annotated datasets.<n>We present FA-Seg, a training-free framework for open-vocabulary segmentation based on diffusion models.
  arXiv  Detail & Related papers  (2025-06-29T16:41:41Z)
• Transformers with Joint Tokens and Local-Global Attention for Efficient Human Pose Estimation [34.99437411281915]
  This paper proposes two ViT-based models for accurate, efficient, and robust 2D pose estimation.<n> Experiments on six benchmarks demonstrate that the proposed methods significantly outperform state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-02-28T22:34:22Z)
• Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation [67.85309547416155]
  A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions.<n>With efficiency being a high priority for scaling such models, we observed that the state-of-the-art method Mask2Former uses 50% of its compute only on the transformer encoder.<n>This is due to the retention of a full-length token-level representation of all backbone feature scales at each encoder layer.
  arXiv  Detail & Related papers  (2024-04-23T01:34:20Z)
• SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers [76.13755422671822]
  This paper investigates the capability of plain Vision Transformers (ViTs) for semantic segmentation using the encoder-decoder framework. We introduce a novel Attention-to-Mask (atm) module to design a lightweight decoder effective for plain ViT. Our decoder outperforms the popular decoder UPerNet using various ViT backbones while consuming only about $5%$ of the computational cost.
  arXiv  Detail & Related papers  (2023-06-09T22:29:56Z)
• Lightweight and Progressively-Scalable Networks for Semantic Segmentation [100.63114424262234]
  Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. In this paper, we thoroughly analyze the design of convolutional blocks and the ways of interactions across multiple scales. We devise Lightweight and Progressively-Scalable Networks (LPS-Net) that novelly expands the network complexity in a greedy manner.
  arXiv  Detail & Related papers  (2022-07-27T16:00:28Z)
• EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction [67.11722682878722]
  This work presents EfficientViT, a new family of high-resolution vision models with novel multi-scale linear attention. Our multi-scale linear attention achieves the global receptive field and multi-scale learning. EfficientViT delivers remarkable performance gains over previous state-of-the-art models.
  arXiv  Detail & Related papers  (2022-05-29T20:07:23Z)
• InverseForm: A Loss Function for Structured Boundary-Aware Segmentation [80.39674800972182]
  We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network. This plug-in loss term complements the cross-entropy loss in capturing boundary transformations. We analyze the quantitative and qualitative effects of our loss function on three indoor and outdoor segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-04-06T18:52:45Z)

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.