Pith. sign in

REVIEW 7 cited by

Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.11837 v1 pith:OF3N5QAQ submitted 2024-06-17 cs.CV

classification cs.CV
keywords codebookimagesizeutilizationmodelratevqganvqgan-lc
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In the realm of image quantization exemplified by VQGAN, the process encodes images into discrete tokens drawn from a codebook with a predefined size. Recent advancements, particularly with LLAMA 3, reveal that enlarging the codebook significantly enhances model performance. However, VQGAN and its derivatives, such as VQGAN-FC (Factorized Codes) and VQGAN-EMA, continue to grapple with challenges related to expanding the codebook size and enhancing codebook utilization. For instance, VQGAN-FC is restricted to learning a codebook with a maximum size of 16,384, maintaining a typically low utilization rate of less than 12% on ImageNet. In this work, we propose a novel image quantization model named VQGAN-LC (Large Codebook), which extends the codebook size to 100,000, achieving an utilization rate exceeding 99%. Unlike previous methods that optimize each codebook entry, our approach begins with a codebook initialized with 100,000 features extracted by a pre-trained vision encoder. Optimization then focuses on training a projector that aligns the entire codebook with the feature distributions of the encoder in VQGAN-LC. We demonstrate the superior performance of our model over its counterparts across a variety of tasks, including image reconstruction, image classification, auto-regressive image generation using GPT, and image creation with diffusion- and flow-based generative models. Code and models are available at https://github.com/zh460045050/VQGAN-LC.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Hita: Holistic Tokenizer for Autoregressive Image Generation

    cs.CV 2025-07 conditional novelty 7.0 of 10

    Hita's holistic-to-local tokenization lets vanilla autoregressive image models generate global tokens first, improving FID, convergence, and enabling zero-shot style transfer and inpainting.

  2. Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A training-only ViT-based projector, VQBridge, combined with learning annealing, achieves full codebook utilization in vector-quantized networks at large codebook sizes, improving reconstruction and autoregressive ima...

  3. Quantize-then-Rectify: Efficient VQ-VAE Training

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A pretrained VAE can be converted into a high-compression VQ-VAE by freezing it and training only a multi-group quantizer plus a post rectifier, cutting training cost by over two orders of magnitude while keeping rFID...

  4. Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis

    cs.CV 2025-07 conditional novelty 6.0 of 10

    DisCon treats discrete image tokens as conditioning signals rather than targets, letting a continuous autoregressive model refine details and reach gFID 1.38 on ImageNet-256.

  5. UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    UniCode² builds a 500K-entry codebook from clustered SigLIP embeddings and uses a cascaded frozen-plus-trainable codebook to unify multimodal understanding and generation with stable training and high token utilization.

  6. MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation

    cs.SD 2025-05 conditional novelty 5.0 of 10

    A single-layer streaming Transformer codec with masked Gaussian noise injection during training reports state-of-the-art reconstruction and better downstream generation and understanding in 16 kHz English speech.

  7. UniTTS: An end-to-end TTS system without decoupling of acoustic and semantic information

    cs.SD 2025-05 conditional novelty 5.0 of 10

    The authors propose DistilCodec, a 32,768-code single-codebook audio codec, and UniTTS, a Qwen2.5-7B TTS model trained with audio, text, and cross-modal autoregressive tasks on interleaved prompts.

Pith tools