paper-with-me

홈 › Papers

MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution

2024-05-28 · Wenzhuo LIU, Fei Zhu, Shijie Ma, Cheng-Lin Liu

Although Vision Transformers (ViTs) have recently advanced computer vision tasks significantly, an important real-world problem was overlooked: adapting to variable input resolutions. Typically, images are resized to a fixed resolution, such as 224x224, for efficiency during training and inference. However, uniform input size conflicts with real-world scenarios where images naturally vary in resolution. Modifying the preset resolution of a model may severely degrade the performance. In this work, we propose to enhance the model adaptability to resolution variation by optimizing the patch embedding. The proposed method, called Multi-Scale Patch Embedding (MSPE), substitutes the standard patch embedding with multiple variable-sized patch kernels and selects the best parameters for different resolutions, eliminating the need to resize the original image. Our method does not require high-cost training or modifications to other parts, making it easy to apply to most ViT models. Experiments in image classification, segmentation, and detection tasks demonstrate the effectiveness of MSPE, yielding superior performance on low-resolution inputs and performing comparably on high-resolution inputs with existing methods.

📄 PDF Abstract BibTeX arXiv:2405.18240

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Two-Stream Regression Network for Dental Implant Position Prediction

2023-05-17 · Xinquan Yang, Xuguang Li, Xuechen Li, WenTing Chen 외

In implant prosthesis treatment, the design of the surgical guide heavily relies on the manual location of the implant position, which is subjective and prone to doctor's experiences. When deep learning based methods has…

PositionPosition regressionPredictionregression

StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning

2024-06-05 · Shaolei Zhang, Qingkai Fang, Shoutao Guo, Zhengrui Ma 외

Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication. Beyond accomplishin…

Automatic Speech Recognition (ASR)de-enes-enfr-en+11

Attention to Burstiness: Low-Rank Bilinear Prompt Tuning

2025-06-28 · Yuzhu Wang, Manni Duan, Shu Kong

Visual Prompt Tuning (VPT) is a parameter-efficient fune-tuning technique that adapts a pre-trained vision Transformer (ViT) by learning a small set of parameters in the input space, known as prompts. In VPT, we uncover …

Visual Prompt Tuning

Future Aware Safe Active Learning of Time Varying Systems using Gaussian Processes

2024-05-17 · Markus Lange-Hegermann, Christoph Zimmer

Experimental exploration of high-cost systems with safety constraints, common in engineering applications, is a challenging endeavor. Data-driven models offer a promising solution, but acquiring the requisite data remain…

Active LearningGaussian Processes

MMSpec: Benchmarking Speculative Decoding for Vision-Language Models

2026-03-16 · Hui Shen, Xin Wang, Ping Zhang, Yunta Hsieh 외 arxiv

Vision-language models (VLMs) achieve strong performance on multimodal tasks but suffer from high inference latency due to large model sizes and long multimodal contexts. Speculative decoding has recently emerged as an e…