Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers

• URL: http://arxiv.org/abs/2412.16553v4
• Date: Thu, 03 Jul 2025 23:00:36 GMT
• Title: Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
• Authors: Yunshan Zhong, Yuyao Zhou, Yuxin Zhang, Wanchen Sui, Shen Li, Yong Li, Fei Chao, Rongrong Ji,
• Abstract summary: Data-free quantization (DFQ) enables model quantization without accessing real data, addressing concerns regarding data security and privacy.<n>With the growing adoption of Vision Transformers (ViTs), DFQ for ViTs has garnered significant attention.<n>We propose SARDFQ, a novel Semantics Alignment and Reinforcement Data-Free Quantization method for ViTs.
• Score: 58.14748181398049
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data-free quantization (DFQ) enables model quantization without accessing real data, addressing concerns regarding data security and privacy. With the growing adoption of Vision Transformers (ViTs), DFQ for ViTs has garnered significant attention. However, existing DFQ methods exhibit two limitations: (1) semantic distortion, where the semantics of synthetic images deviate substantially from those of real images, and (2) semantic inadequacy, where synthetic images contain extensive regions with limited content and oversimplified textures, leading to suboptimal quantization performance. To address these limitations, we propose SARDFQ, a novel Semantics Alignment and Reinforcement Data-Free Quantization method for ViTs. To address semantic distortion, SARDFQ incorporates Attention Priors Alignment (APA), which optimizes synthetic images to follow randomly generated structure attention priors. To mitigate semantic inadequacy, SARDFQ introduces Multi-Semantic Reinforcement (MSR), leveraging localized patch optimization to enhance semantic richness across synthetic images. Furthermore, SARDFQ employs Soft-Label Learning (SL), wherein multiple semantic targets are adapted to facilitate the learning of multi-semantic images augmented by MSR. Extensive experiments demonstrate the effectiveness of SARDFQ, significantly surpassing existing methods. For example, SARDFQ improves top-1 accuracy on ImageNet by 15.52% for W4A4 ViT-B. The code is at https://github.com/zysxmu/SARDFQ.

Related papers

• Text-Visual Semantic Constrained AI-Generated Image Quality Assessment [47.575342788480505]
  We propose a unified framework to enhance the comprehensive evaluation of both text-image consistency and perceptual distortion in AI-generated images.<n>Our approach integrates key capabilities from multiple models and tackles the aforementioned challenges by introducing two core modules.<n>Tests conducted on multiple benchmark datasets demonstrate that SC-AGIQA outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-07-14T16:21:05Z)
• Data-Efficient Generalization for Zero-shot Composed Image Retrieval [67.46975191141928]
  ZS-CIR aims to retrieve the target image based on a reference image and a text description without requiring in-distribution triplets for training.<n>One prevalent approach follows the vision-language pretraining paradigm that employs a mapping network to transfer the image embedding to a pseudo-word token in the text embedding space.<n>We propose a Data-efficient Generalization (DeG) framework, including two novel designs, namely, Textual Supplement (TS) module and Semantic-Set (S-Set)
  arXiv  Detail & Related papers  (2025-03-07T07:49:31Z)
• SQ-GAN: Semantic Image Communications Using Masked Vector Quantization [55.02795214161371]
  This work introduces Semantically Masked VQ-GAN (SQ-GAN), a novel approach to optimize image compression for semantic/task-oriented communications. SQ-GAN employs off-the-shelf semantic semantic segmentation and a new semantic-conditioned adaptive mask module (SAMM) to selectively encode semantically significant features of the images.
  arXiv  Detail & Related papers  (2025-02-13T17:35:57Z)
• Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning [70.98890307376548]
  We propose a novel Patch-wise Cross-modal feature Mix-up (PCM) mechanism to adaptively mitigate the unfaithful contents during training. Our PCM-Net ranks first in both in-domain and cross-domain zero-shot image captioning.
  arXiv  Detail & Related papers  (2024-12-31T13:39:08Z)
• Vision Transformer-based Semantic Communications With Importance-Aware Quantization [13.328970689723096]
  This paper presents a vision transformer (ViT)-based semantic communication system with importance-aware quantization (IAQ) for wireless image transmission. We show that our IAQ framework outperforms conventional image compression methods in both error-free and realistic communication scenarios.
  arXiv  Detail & Related papers  (2024-12-08T19:24:47Z)
• Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation [54.96563068182733]
  We propose Modality Adaptation with text-to-image Diffusion Models (MADM) for semantic segmentation task. MADM utilizes text-to-image diffusion models pre-trained on extensive image-text pairs to enhance the model's cross-modality capabilities. We show that MADM achieves state-of-the-art adaptation performance across various modality tasks, including images to depth, infrared, and event modalities.
  arXiv  Detail & Related papers  (2024-10-29T03:49:40Z)
• Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval [92.13664084464514]
  The task of composed image retrieval (CIR) aims to retrieve images based on the query image and the text describing the users' intent. Existing methods have made great progress with the advanced large vision-language (VL) model in CIR task, however, they generally suffer from two main issues: lack of labeled triplets for model training and difficulty of deployment on resource-restricted environments. We propose Image2Sentence based Asymmetric zero-shot composed image retrieval (ISA), which takes advantage of the VL model and only relies on unlabeled images for composition learning.
  arXiv  Detail & Related papers  (2024-03-03T07:58:03Z)
• Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection [13.840950434728533]
  State-of-the-art Synthetic Image Detection (SID) research has led to strong evidence on the advantages of feature extraction from foundation models. We leverage the image representations extracted by intermediate Transformer blocks of CLIP's image-encoder via a lightweight network. Our method is compared against the state-of-the-art by evaluating it on 20 test datasets and exhibits an average +10.6% absolute performance improvement.
  arXiv  Detail & Related papers  (2024-02-29T12:18:43Z)
• Semantic-aware Data Augmentation for Text-to-image Synthesis [19.28143363034362]
  In text-to-image synthesis (T2Isyn), augmentation wisdom still suffers from the semantic mismatch between augmented paired data. In this paper, we develop a novel Semantic-aware Data Augmentation framework dedicated to T2Isyn.
  arXiv  Detail & Related papers  (2023-12-13T07:57:40Z)
• Robustness-Guided Image Synthesis for Data-Free Quantization [15.91924736452861]
  We propose Robustness-Guided Image Synthesis (RIS) to enrich the semantics of synthetic images and improve image diversity. RIS is a simple but effective method to enrich the semantics of synthetic images and improve image diversity. We achieve state-of-the-art performance for various settings on data-free quantization and can be extended to other data-free compression tasks.
  arXiv  Detail & Related papers  (2023-10-05T16:39:14Z)
• Beyond Learned Metadata-based Raw Image Reconstruction [86.1667769209103]
  Raw images have distinct advantages over sRGB images, e.g., linearity and fine-grained quantization levels. They are not widely adopted by general users due to their substantial storage requirements. We propose a novel framework that learns a compact representation in the latent space, serving as metadata.
  arXiv  Detail & Related papers  (2023-06-21T06:59:07Z)
• Improving Scene Text Image Super-resolution via Dual Prior Modulation Network [20.687100711699788]
  Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images. Existing approaches neglect the global structure of the text, which bounds the semantic determinism of the scene text. Our work proposes a plug-and-play module dubbed Dual Prior Modulation Network (DPMN), which leverages dual image-level priors to bring performance gain over existing approaches.
  arXiv  Detail & Related papers  (2023-02-21T02:59:37Z)
• Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification [48.640470032205265]
  We propose SGID, a Semantic-guided Generative Image augmentation method with Diffusion models for image classification. Specifically, SGID employs diffusion models to generate augmented images with good image diversity. More importantly, SGID takes image labels and captions as guidance to maintain semantic consistency between the augmented and original images.
  arXiv  Detail & Related papers  (2023-02-04T02:47:41Z)
• Towards Better Text-Image Consistency in Text-to-Image Generation [15.735515302139335]
  We develop a novel CLIP-based metric termed as Semantic Similarity Distance (SSD) We further design the Parallel Deep Fusion Generative Adversarial Networks (PDF-GAN), which can fuse semantic information at different granularities. Our PDF-GAN can lead to significantly better text-image consistency while maintaining decent image quality on the CUB and COCO datasets.
  arXiv  Detail & Related papers  (2022-10-27T07:47:47Z)
• Towards Semantic Communications: Deep Learning-Based Image Semantic Coding [42.453963827153856]
  We conceive the semantic communications for image data that is much more richer in semantics and bandwidth sensitive. We propose an reinforcement learning based adaptive semantic coding (RL-ASC) approach that encodes images beyond pixel level. Experimental results demonstrate that the proposed RL-ASC is noise robust and could reconstruct visually pleasant and semantic consistent image.
  arXiv  Detail & Related papers  (2022-08-08T12:29:55Z)
• Semantic Image Synthesis via Diffusion Models [159.4285444680301]
  Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks. Recent work on semantic image synthesis mainly follows the emphde facto Generative Adversarial Nets (GANs)
  arXiv  Detail & Related papers  (2022-06-30T18:31:51Z)
• Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform [58.60004238261117]
  We propose a versatile deep image compression network based on Spatial Feature Transform (SFT arXiv:1804.02815) Our model covers a wide range of compression rates using a single model, which is controlled by arbitrary pixel-wise quality maps. The proposed framework allows us to perform task-aware image compressions for various tasks.
  arXiv  Detail & Related papers  (2021-08-21T17:30:06Z)

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.