"Principal Components" Enable A New Language of Images

• URL: http://arxiv.org/abs/2503.08685v1
• Date: Tue, 11 Mar 2025 17:59:41 GMT
• Title: "Principal Components" Enable A New Language of Images
• Authors: Xin Wen, Bingchen Zhao, Ismail Elezi, Jiankang Deng, Xiaojuan Qi,
• Abstract summary: We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space.<n>Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
• Score: 79.45806370905775
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space. While existing visual tokenizers primarily optimize for reconstruction fidelity, they often neglect the structural properties of the latent space -- a critical factor for both interpretability and downstream tasks. Our method generates a 1D causal token sequence for images, where each successive token contributes non-overlapping information with mathematically guaranteed decreasing explained variance, analogous to principal component analysis. This structural constraint ensures the tokenizer extracts the most salient visual features first, with each subsequent token adding diminishing yet complementary information. Additionally, we identified and resolved a semantic-spectrum coupling effect that causes the unwanted entanglement of high-level semantic content and low-level spectral details in the tokens by leveraging a diffusion decoder. Experiments demonstrate that our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system. Moreover, auto-regressive models trained on our token sequences achieve performance comparable to current state-of-the-art methods while requiring fewer tokens for training and inference.

Related papers

• Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation [63.89280381800457]
  We propose TokenBridge, which maintains the strong representation capacity of continuous tokens while preserving the modeling simplicity of discrete tokens. We introduce a dimension-wise quantization strategy that independently discretizes each feature dimension, paired with a lightweight autoregressive prediction mechanism. Our approach achieves reconstruction and generation quality on par with continuous methods while using standard categorical prediction.
  arXiv  Detail & Related papers  (2025-03-20T17:59:59Z)
• CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis [8.386261591495103]
  We introduce CoCoNO, a new algorithm that optimize the initial latent by leveraging the complementary information within self-attention and cross-attention maps. Our method introduces two new loss functions: the attention contrast loss, which minimizes undesirable overlap by ensuring each self-attention segment is exclusively linked to a specific subject's cross attention map, and the attention complete loss, which maximizes the activation within these segments to guarantee that each subject is fully and distinctly represented.
  arXiv  Detail & Related papers  (2024-11-25T08:20:14Z)
• LLM-based Hierarchical Concept Decomposition for Interpretable Fine-Grained Image Classification [5.8754760054410955]
  We introduce textttHi-CoDecomposition, a novel framework designed to enhance model interpretability through structured concept analysis. Our approach not only aligns with the performance of state-of-the-art models but also advances transparency by providing clear insights into the decision-making process.
  arXiv  Detail & Related papers  (2024-05-29T00:36:56Z)
• Deep Common Feature Mining for Efficient Video Semantic Segmentation [25.851900402539467]
  We present Deep Common Feature Mining (DCFM) for video semantic segmentation.<n>DCFM explicitly decomposes features into two complementary components.<n>We incorporate a self-supervised loss function to reinforce intra-class feature similarity and enhance temporal consistency.
  arXiv  Detail & Related papers  (2024-03-05T06:17:59Z)
• Subobject-level Image Tokenization [60.80949852899857]
  Patch-based image tokenization ignores the morphology of the visual world. Inspired by subword tokenization, we introduce subobject-level adaptive token segmentation. We show that subobject tokenization enables faster convergence and better generalization while using fewer visual tokens.
  arXiv  Detail & Related papers  (2024-02-22T06:47:44Z)
• Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement [58.9768112704998]
  Disentangled representation learning strives to extract the intrinsic factors within observed data. We introduce a new perspective and framework, demonstrating that diffusion models with cross-attention can serve as a powerful inductive bias. This is the first work to reveal the potent disentanglement capability of diffusion models with cross-attention, requiring no complex designs.
  arXiv  Detail & Related papers  (2024-02-15T05:07:54Z)
• UGMAE: A Unified Framework for Graph Masked Autoencoders [67.75493040186859]
  We propose UGMAE, a unified framework for graph masked autoencoders. We first develop an adaptive feature mask generator to account for the unique significance of nodes. We then design a ranking-based structure reconstruction objective joint with feature reconstruction to capture holistic graph information.
  arXiv  Detail & Related papers  (2024-02-12T19:39:26Z)
• Attribute-Aware Deep Hashing with Self-Consistency for Large-Scale Fine-Grained Image Retrieval [65.43522019468976]
  We propose attribute-aware hashing networks with self-consistency for generating attribute-aware hash codes. We develop an encoder-decoder structure network of a reconstruction task to unsupervisedly distill high-level attribute-specific vectors. Our models are equipped with a feature decorrelation constraint upon these attribute vectors to strengthen their representative abilities.
  arXiv  Detail & Related papers  (2023-11-21T08:20:38Z)
• Deep Semantic Statistics Matching (D2SM) Denoising Network [70.01091467628068]
  We introduce the Deep Semantic Statistics Matching (D2SM) Denoising Network. It exploits semantic features of pretrained classification networks, then it implicitly matches the probabilistic distribution of clear images at the semantic feature space. By learning to preserve the semantic distribution of denoised images, we empirically find our method significantly improves the denoising capabilities of networks.
  arXiv  Detail & Related papers  (2022-07-19T14:35:42Z)
• Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval [17.422973861218182]
  Unsupervised image retrieval aims to learn an efficient retrieval system without expensive data annotations. Recent advance proposes deep fully unsupervised image retrieval aiming at training a deep model from scratch to jointly optimize visual features and quantization codes. We propose a novel self-supervised consistent quantization approach to deep fully unsupervised image retrieval, which consists of part consistent quantization and global consistent quantization.
  arXiv  Detail & Related papers  (2022-06-20T14:39:59Z)
• Synthetic Convolutional Features for Improved Semantic Segmentation [139.5772851285601]
  We suggest to generate intermediate convolutional features and propose the first synthesis approach that is catered to such intermediate convolutional features. This allows us to generate new features from label masks and include them successfully into the training procedure. Experimental results and analysis on two challenging datasets Cityscapes and ADE20K show that our generated feature improves performance on segmentation tasks.
  arXiv  Detail & Related papers  (2020-09-18T14:12:50Z)

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.