PTQ4SAM: Post-Training Quantization for Segment Anything
- URL: http://arxiv.org/abs/2405.03144v1
- Date: Mon, 6 May 2024 03:39:50 GMT
- Title: PTQ4SAM: Post-Training Quantization for Segment Anything
- Authors: Chengtao Lv, Hong Chen, Jinyang Guo, Yifu Ding, Xianglong Liu,
- Abstract summary: Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks.
However, as a large-scale model, the immense memory and computation costs hinder its practical deployment.
We propose a post-training quantization framework for Segment Anything Model, namely PTQ4SAM.
- Score: 28.893095276574893
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks. However, as a large-scale model, the immense memory and computation costs hinder its practical deployment. In this paper, we propose a post-training quantization (PTQ) framework for Segment Anything Model, namely PTQ4SAM. First, we investigate the inherent bottleneck of SAM quantization attributed to the bimodal distribution in post-Key-Linear activations. We analyze its characteristics from both per-tensor and per-channel perspectives, and propose a Bimodal Integration strategy, which utilizes a mathematically equivalent sign operation to transform the bimodal distribution into a relatively easy-quantized normal distribution offline. Second, SAM encompasses diverse attention mechanisms (i.e., self-attention and two-way cross-attention), resulting in substantial variations in the post-Softmax distributions. Therefore, we introduce an Adaptive Granularity Quantization for Softmax through searching the optimal power-of-two base, which is hardware-friendly. Extensive experimental results across various vision tasks (instance segmentation, semantic segmentation and object detection), datasets and model variants show the superiority of PTQ4SAM. For example, when quantizing SAM-L to 6-bit, we achieve lossless accuracy for instance segmentation, about 0.5\% drop with theoretical 3.9$\times$ acceleration. The code is available at \url{https://github.com/chengtao-lv/PTQ4SAM}.
Related papers
- Moving Object Segmentation: All You Need Is SAM (and Flow) [82.78026782967959]
We investigate two models for combining SAM with optical flow that harness the segmentation power of SAM with the ability of flow to discover and group moving objects.
In the first model, we adapt SAM to take optical flow, rather than RGB, as an input. In the second, SAM takes RGB as an input, and flow is used as a segmentation prompt.
These surprisingly simple methods, without any further modifications, outperform all previous approaches by a considerable margin in both single and multi-object benchmarks.
arXiv Detail & Related papers (2024-04-18T17:59:53Z) - WSI-SAM: Multi-resolution Segment Anything Model (SAM) for histopathology whole-slide images [8.179859593451285]
We present WSI-SAM, enhancing Segment Anything Model (SAM) with precise object segmentation capabilities for histopathology images.
To fully exploit pretrained knowledge while minimizing training overhead, we keep SAM frozen, introducing only minimal extra parameters.
Our model outperforms SAM by 4.1 and 2.5 percent points on a ductal carcinoma in situ (DCIS) segmentation tasks and breast cancer metastasis segmentation task.
arXiv Detail & Related papers (2024-03-14T10:30:43Z) - TinySAM: Pushing the Envelope for Efficient Segment Anything Model [76.21007576954035]
We propose a framework to obtain a tiny segment anything model (TinySAM) while maintaining the strong zero-shot performance.
We first propose a full-stage knowledge distillation method with hard prompt sampling and hard mask weighting strategy to distill a lightweight student model.
We also adapt the post-training quantization to the promptable segmentation task and further reduce the computational cost.
arXiv Detail & Related papers (2023-12-21T12:26:11Z) - Stable Segment Anything Model [79.9005670886038]
The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts.
This paper presents the first comprehensive analysis on SAM's segmentation stability across a diverse spectrum of prompt qualities.
Our solution, termed Stable-SAM, offers several advantages: 1) improved SAM's segmentation stability across a wide range of prompt qualities, while 2) retaining SAM's powerful promptable segmentation efficiency and generality.
arXiv Detail & Related papers (2023-11-27T12:51:42Z) - SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding [40.40630116715132]
The landscape of publicly available vision foundation models (VFMs) is expanding rapidly.
We introduce a simple recipe to efficiently merge VFMs into a unified model that absorbs their expertise.
By applying our method to SAM and CLIP, we obtain SAM-CLIP: a unified model that combines the capabilities of SAM and CLIP into a single vision transformer.
arXiv Detail & Related papers (2023-10-23T19:21:57Z) - MatFormer: Nested Transformer for Elastic Inference [94.1789252941718]
MatFormer is a nested Transformer architecture designed to offer elasticity in a variety of deployment constraints.
We show that a 2.6B decoder-only MatFormer language model (MatLM) allows us to extract smaller models spanning from 1.5B to 2.6B.
We also observe that smaller encoders extracted from a universal MatFormer-based ViT (MatViT) encoder preserve the metric-space structure for adaptive large-scale retrieval.
arXiv Detail & Related papers (2023-10-11T17:57:14Z) - Semantic-SAM: Segment and Recognize Anything at Any Granularity [83.64686655044765]
We introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity.
We consolidate multiple datasets across three granularities and introduce decoupled classification for objects and parts.
For the multi-granularity capability, we propose a multi-choice learning scheme during training, enabling each click to generate masks at multiple levels.
arXiv Detail & Related papers (2023-07-10T17:59:40Z) - SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference.
We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit.
Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
arXiv Detail & Related papers (2023-06-13T08:57:54Z)
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.