相关论文: Early Semantic Grounding in Image Editing Models f…

Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent…

Interactive image segmentation(IIS) plays a critical role in generating precise annotations for remote sensing imagery, where objects often exhibit scale variations, irregular boundaries and complex backgrounds. However, existing IIS…

Vision-language pretraining on large datasets of images-text pairs is one of the main building blocks of current Vision-Language Models. While with additional training, these models excel in various downstream tasks, including visual…

Implicit representation of an image can map arbitrary coordinates in the continuous domain to their corresponding color values, presenting a powerful capability for image reconstruction. Nevertheless, existing implicit representation…

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose…

GUI grounding is a critical capability for vision-language models (VLMs) that enables automated interaction with graphical user interfaces by locating target elements from natural language instructions. However, grounding on GUI screenshots…

Semantic segmentation has a broad range of applications, but its real-world impact has been significantly limited by the prohibitive annotation costs necessary to enable deployment. Segmentation methods that forgo supervision can side-step…

Vision-Language Models for remote sensing have shown promising uses thanks to their extensive pretraining. However, their conventional usage in zero-shot scene classification methods still involves dividing large images into patches and…

Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks. This is a weakness of current zero-shot learning frameworks as…

Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixel-level prediction…

Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as…

We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-to-image retrieval as a `downstream' task to guide the process of phrase…

Pre-trained image editing models exhibit strong spatial reasoning and object-aware transformation capabilities acquired from billions of image-text pairs, yet they possess no explicit temporal modeling. This paper demonstrates that these…

We investigate the problem of Language-Based Image Editing (LBIE). Given a source image and a natural language description, we want to generate a target image by editing the source image based on the description. We propose a generic…

This paper presents a "learning to learn" approach to figure-ground image segmentation. By exploring webly-abundant images of specific visual effects, our method can effectively learn the visual-effect internal representations in an…

Vision-and-language models trained to match images with text can be combined with visual explanation methods to point to the locations of specific objects in an image. Our work shows that the localization --"grounding"-- abilities of these…

Visual grounding tasks aim to localize image regions based on natural language references. In this work, we explore whether generative VLMs predominantly trained on image-text data could be leveraged to scale up the text annotation of…

Deep neural network-based semantic segmentation generally requires large-scale cost extensive annotations for training to obtain better performance. To avoid pixel-wise segmentation annotations which are needed for most methods, recently…

Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise…