Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding

• URL: http://arxiv.org/abs/2403.18593v2
• Date: Sun, 13 Oct 2024 03:01:11 GMT
• Title: Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding
• Authors: Run Shao, Zhaoyang Zhang, Chao Tao, Yunsheng Zhang, Chengli Peng, Haifeng Li,
• Abstract summary: The tokenizer, as one of the fundamental components of large models, has long been overlooked or even misunderstood in visual tasks. We design a simple HOmogeneous visual tOKenizer: HOOK. To achieve homogeneity, the OPM splits the image into 4*4 pixel seeds and then utilizes the attention mechanism to perceive SIRs. The OVM defines a variable number of learnable vectors as cross-attention queries, allowing for the adjustment of token quantity.
• Score: 13.920198434637223
• License:
• Abstract: The tokenizer, as one of the fundamental components of large models, has long been overlooked or even misunderstood in visual tasks. One key factor of the great comprehension power of the large language model is that natural language tokenizers utilize meaningful words or subwords as the basic elements of language. In contrast, mainstream visual tokenizers, represented by patch-based methods such as Patch Embed, rely on meaningless rectangular patches as basic elements of vision, which cannot serve as effectively as words or subwords in language. Starting from the essence of the tokenizer, we defined semantically independent regions (SIRs) for vision. We designed a simple HOmogeneous visual tOKenizer: HOOK. HOOK mainly consists of two modules: the Object Perception Module (OPM) and the Object Vectorization Module (OVM). To achieve homogeneity, the OPM splits the image into 4*4 pixel seeds and then utilizes the attention mechanism to perceive SIRs. The OVM employs cross-attention to merge seeds within the same SIR. To achieve adaptability, the OVM defines a variable number of learnable vectors as cross-attention queries, allowing for the adjustment of token quantity. We conducted experiments on the NWPU-RESISC45, WHU-RS19 classification dataset, and GID5 segmentation dataset for sparse and dense tasks. The results demonstrate that the visual tokens obtained by HOOK correspond to individual objects, which demonstrates homogeneity. HOOK outperformed Patch Embed by 6\% and 10\% in the two tasks and achieved state-of-the-art performance compared to the baselines used for comparison. Compared to Patch Embed, which requires more than one hundred tokens for one image, HOOK requires only 6 and 8 tokens for sparse and dense tasks, respectively, resulting in efficiency improvements of 1.5 to 2.8 times. The code is available at https://github.com/GeoX-Lab/Hook.

Related papers

• VisMin: Visual Minimal-Change Understanding [7.226130826257802]
  We introduce a new, challenging benchmark termed textbfVisual textbfMinimal-Change Understanding (VisMin) VisMin requires models to predict the correct image-caption match given two images and two captions. We generate a large-scale training dataset to finetune CLIP and Idefics2, showing significant improvements in fine-grained understanding across benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T18:10:43Z)
• Towards Semantic Equivalence of Tokenization in Multimodal LLM [149.11720372278273]
  Vision tokenization is essential for semantic alignment between vision and language. This paper proposes a novel dynamic Semantic-Equivalent Vision Tokenizer (SeTok) SeTok groups visual features into semantic units via a dynamic clustering algorithm. The resulting vision tokens effectively preserve semantic integrity and capture both low-frequency and high-frequency visual features.
  arXiv  Detail & Related papers  (2024-06-07T17:55:43Z)
• Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment [40.63340635482609]
  Existing image-text modality alignment in Vision Language Models (VLMs) treats each text token equally in an autoregressive manner. We advocate for assigning distinct contributions for each text token based on its visual correlation. We introduce Contrastive ALignment (CAL), a simple yet effective re-weighting strategy that prioritizes training visually correlated tokens.
  arXiv  Detail & Related papers  (2024-05-28T06:44:13Z)
• Accelerating Transformers with Spectrum-Preserving Token Merging [43.463808781808645]
  PiToMe prioritizes the preservation of informative tokens using an additional metric termed the energy score. Experimental findings demonstrate that PiToMe saved from 40-60% FLOPs of the base models.
  arXiv  Detail & Related papers  (2024-05-25T09:37:01Z)
• AiluRus: A Scalable ViT Framework for Dense Prediction [95.1313839257891]
  Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. We propose to apply adaptive resolution for different regions in the image according to their importance. We evaluate our proposed method on three different datasets and observe promising performance.
  arXiv  Detail & Related papers  (2023-11-02T12:48:43Z)
• STAIR: Learning Sparse Text and Image Representation in Grounded Tokens [84.14528645941128]
  We show that it is possible to build a sparse semantic representation that is as powerful as, or even better than, dense presentations. We extend the CLIP model and build a sparse text and image representation (STAIR), where the image and text are mapped to a sparse token space. It significantly outperforms a CLIP model with +$4.9%$ and +$4.3%$ absolute Recall@1 improvement.
  arXiv  Detail & Related papers  (2023-01-30T17:21:30Z)
• BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers [117.79456335844439]
  We propose to use a semantic-rich visual tokenizer as the reconstruction target for masked prediction. We then pretrain vision Transformers by predicting the original visual tokens for the masked image patches. Experiments on image classification and semantic segmentation show that our approach outperforms all compared MIM methods.
  arXiv  Detail & Related papers  (2022-08-12T16:48:10Z)
• Patch-level Representation Learning for Self-supervised Vision Transformers [68.8862419248863]
  Vision Transformers (ViTs) have gained much attention recently as a better architectural choice, often outperforming convolutional networks for various visual tasks. Inspired by this, we design a simple yet effective visual pretext task, coined SelfPatch, for learning better patch-level representations. We demonstrate that SelfPatch can significantly improve the performance of existing SSL methods for various visual tasks.
  arXiv  Detail & Related papers  (2022-06-16T08:01:19Z)
• Single-Stream Multi-Level Alignment for Vision-Language Pretraining [103.09776737512078]
  We propose a single stream model that aligns the modalities at multiple levels. We achieve this using two novel tasks: symmetric cross-modality reconstruction and a pseudo-labeled key word prediction. We demonstrate top performance on a set of Vision-Language downstream tasks such as zero-shot/fine-tuned image/text retrieval, referring expression, and VQA.
  arXiv  Detail & Related papers  (2022-03-27T21:16:10Z)
• PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers [9.63371509052453]
  This paper proposes to learn Patch-to-Cluster attention (PaCa) in Vision Transformers (ViT) The proposed PaCa module is used in designing efficient and interpretable ViT backbones and semantic segmentation head networks. It is significantly more efficient than PVT models in MS-COCO and MIT-ADE20k due to the linear complexity.
  arXiv  Detail & Related papers  (2022-03-22T18:28:02Z)

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.