Related papers: OneFormer: One Transformer to Rule Universal Image…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…

There is a recent trend in the LiDAR perception field towards unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks for each task. In this paper, we introduce a new LiDAR…

Image fusion is a technique to integrate information from multiple source images with complementary information to improve the richness of a single image. Due to insufficient task-specific training data and corresponding ground truth, most…

Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot run in real-time, and simplifying these architectures to…

Due to the high similarity between camouflaged instances and the background, the recently proposed camouflaged instance segmentation (CIS) faces challenges in accurate localization and instance segmentation. To this end, inspired by…

Panoptic Part Segmentation (PPS) unifies panoptic and part segmentation into one task. Previous works utilize separate approaches to handle things, stuff, and part predictions without shared computation and task association. We aim to unify…

Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be…

In this paper, we explore the possibility of building a unified foundation model that can be adapted to both vision-only and text-only tasks. Starting from BERT and ViT, we design a unified transformer consisting of modality-specific…

Transformer is a popularly used neural network architecture, especially for language understanding. We introduce an extended and unified architecture that can be used for tasks involving a variety of modalities like image, text, videos,…

Dense image segmentation tasks e.g., semantic, panoptic) are useful for image editing, but existing methods can hardly generalize well in an in-the-wild setting where there are unrestricted image domains, classes, and image resolution and…

Visual segmentation seeks to partition images, video frames, or point clouds into multiple segments or groups. This technique has numerous real-world applications, such as autonomous driving, image editing, robot sensing, and medical…

In this paper, we present the One-shot In-context Part Segmentation (OIParts) framework, designed to tackle the challenges of part segmentation by leveraging visual foundation models (VFMs). Existing training-based one-shot part…

Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.g., STEGO) or class-agnostic…

The CNN-based methods have achieved impressive results in medical image segmentation, but they failed to capture the long-range dependencies due to the inherent locality of the convolution operation. Transformer-based methods are recently…

Large foundation models, known for their strong zero-shot generalization, have excelled in visual and language applications. However, applying them to medical image segmentation, a domain with diverse imaging types and target labels,…

In medical image segmentation, specialized computer vision techniques, notably transformers grounded in attention mechanisms and residual networks employing skip connections, have been instrumental in advancing performance. Nonetheless,…

The universal model emerges as a promising trend for medical image segmentation, paving up the way to build medical imaging large model (MILM). One popular strategy to build universal models is to encode each task as a one-hot vector and…

Current semantic segmentation models have achieved great success under the independent and identically distributed (i.i.d.) condition. However, in real-world applications, test data might come from a different domain than training data.…

Interactive image segmentation enables annotators to efficiently perform pixel-level annotation for segmentation tasks. However, the existing interactive segmentation pipeline suffers from inefficient computations of interactive models…

Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various…