One-D-Piece: Image Tokenizer Meets Quality-Controllable Compression
Current image tokenization methods require a large number of tokens to capture the information contained within images. Although the amount of information varies across images, most image tokenizers only support fixed-length tokenization, leading to inefficiency in token allocation. In this study, we introduce One-D-Piece, a discrete image tokenizer designed for variable-length tokenization, achieving quality-controllable mechanism. To enable variable compression rate, we introduce a simple but effective regularization mechanism named "Tail Token Drop" into discrete one-dimensional image tokenizers. This method encourages critical information to concentrate at the head of the token sequence, enabling support of variadic tokenization, while preserving state-of-the-art reconstruction quality. We evaluate our tokenizer across multiple reconstruction quality metrics and find that it delivers significantly better perceptual quality than existing quality-controllable compression methods, including JPEG and WebP, at smaller byte sizes. Furthermore, we assess our tokenizer on various downstream computer vision tasks, including image classification, object detection, semantic segmentation, and depth estimation, confirming its adaptability to numerous applications compared to other variable-rate methods. Our approach demonstrates the versatility of variable-length discrete image tokenization, establishing a new paradigm in both compression efficiency and reconstruction performance. Finally, we validate the effectiveness of tail token drop via detailed analysis of tokenizers.
Code (0)
등록된 구현이 없습니다.
Tasks
Depth Estimationimage-classificationImage Classificationobject-detectionObject DetectionSemantic SegmentationSimilar Papers 제목 키워드 기반
SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing
This paper describes SentencePiece, a language-independent subword tokenizer and detokenizer designed for Neural-based text processing, including Neural Machine Translation. It provides open-source C++ and Python impleme…
Machine TranslationNMTSegmentationTranslationSemantic Tokenizer for Enhanced Natural Language Processing
Traditionally, NLP performance improvement has been focused on improving models and increasing the number of parameters. Little attention has been paid to vocabulary optimization. We present a novel tokenizer that uses s…
SentenceSentence EmbeddingsMorphological evaluation of subwords vocabulary used by BETO language model
Subword tokenization algorithms used by Large Language Models are significantly more efficient and can independently build the necessary vocabulary of words and subwords without human intervention. However, those subword…
Language ModelingLanguage ModellingSemantic Tokenizer for Enhanced Natural Language Processing
Traditionally, NLP performance improvement has been focused on improving models and increasing the number of model parameters. NLP vocabulary construction has remained focused on maximizing the number of words represente…
SentenceSentence EmbeddingsFlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in imag…
Image GenerationPrediction