Results 1 to 10 of about 403,741 (54)
GLaMM: Pixel Grounding Large Multimodal Model [PDF]
Computer Vision and Pattern Recognition, 2023 Large Multimodal Models (LMMs) extend Large Lan-guage Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses.
H. Rasheed +9 more
semanticscholar +1 more source
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization [PDF]
European Conference on Computer Vision, 2023 Diffusion models have demonstrated impressive performance in various image generation, editing, enhancement and translation tasks. In particular, the pre-trained text-to-image stable diffusion models provide a potential solution to the challenging ...
Tao Yang +3 more
semanticscholar +1 more source
PixelLM: Pixel Reasoning with Large Multimodal Model [PDF]
Computer Vision and Pattern Recognition, 2023 While large multimodal models (LMMs) have achieved remarkable progress, generating pixel-level masks for image reasoning tasks involving multiple open-world targets remains a challenge. To bridge this gap, we introduce PixelLM, an effective and efficient
Zhongwei Ren +6 more
semanticscholar +1 more source
Osprey: Pixel Understanding with Visual Instruction Tuning [PDF]
Computer Vision and Pattern Recognition, 2023 Multimodal large language models (MLLMs) have recently achieved impressive general-purpose vision-language capabilities through visual instruction tuning.
Yuqian Yuan +7 more
semanticscholar +1 more source
Generalized Decoding for Pixel, Image, and Language [PDF]
Computer Vision and Pattern Recognition, 2022 We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly. X-Decoder takes as input two types of queries: (i) generic non-semantic queries and (ii) semantic queries induced from text ...
Xueyan Zou +13 more
semanticscholar +1 more source
Selección de Píxel Semilla mediante Wavelets para Crecimiento por Regiones Difuso
GECONTEC: Revista Internacional de Gestión del Conocimiento y la Tecnología, 2022 El análisis de masas y tumores en mamografía es un problema difícil porque los signos del cáncer pueden ser mínimos o estar superpuestos en el tejido. Las técnicas de procesamiento de imágenes pueden mejorar el diagnóstico reduciendo los costos.
Damian Valdés Santiago +2 more
doaj +1 more source
Exploring Cross-Image Pixel Contrast for Semantic Segmentation [PDF]
IEEE International Conference on Computer Vision, 2021 Current semantic segmentation methods focus only on mining "local" context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention) or structure-aware optimization criteria (
Wenguan Wang +5 more
semanticscholar +1 more source
Pixel Difference Networks for Efficient Edge Detection [PDF]
IEEE International Conference on Computer Vision, 2021 Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection with the rich and abstract edge representation capacities.
Z. Su +7 more
semanticscholar +1 more source
SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022 Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on an unlabeled target domain by utilizing the supervised model trained on a labeled source domain. One popular solution is self-training, which retrains the model with
Binhui Xie +5 more
semanticscholar +1 more source
Pixel-Grounded Prototypical Part Networks [PDF]
IEEE Workshop/Winter Conference on Applications of Computer Vision, 2023 Prototypical part neural networks (ProtoPartNNs), namely ProtoPNet and its derivatives, are an intrinsically interpretable approach to machine learning.
Zachariah Carmichael +5 more
semanticscholar +1 more source