Related papers: PEM: Prototype-based Efficient MaskFormer for Imag…

This study explored the architecture of semantic segmentation and evaluated models that excel in polyp segmentation. We present an integrated framework that harnesses the advantages of different models to attain an optimal outcome.…

We present a new method for efficient high-quality image segmentation of objects and scenes. By analogizing classical computer graphics methods for efficient rendering with over- and undersampling challenges faced in pixel labeling tasks,…

Medical image segmentation is important for computer-aided diagnosis. Good segmentation demands the model to see the big picture and fine details simultaneously, i.e., to learn image features that incorporate large context while keep high…

Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique. The existing MIM methods adopt the strategy to mask random patches of the image and reconstruct the…

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…

This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image. Departing from the prevalent focus on performance…

We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perception (MLP) decoders. SegFormer has two appealing features: 1) SegFormer comprises a novel…

Multi-scale architecture, including hierarchical vision transformer, has been commonly applied to high-resolution semantic segmentation to deal with computational complexity with minimum performance loss. In this paper, we propose a novel…

Cancer detection and prognosis relies heavily on medical imaging, particularly CT and PET scans. Deep Neural Networks (DNNs) have shown promise in tumor segmentation by fusing information from these modalities. However, a critical…

Ensemble of predictions is known to perform better than individual predictions taken separately. However, for tasks that require heavy computational resources, e.g. semantic segmentation, creating an ensemble of learners that needs to be…

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…

Vision Foundation Models (VFMs) pre-trained at scale enable a single frozen encoder to serve multiple downstream tasks simultaneously. Recent VFM-based encoder-only models for image and video segmentation, such as EoMT and VidEoMT, achieve…

Transformers have excelled in many tasks including vision. However, efficient deployment of transformer models in low-latency or high-throughput applications is hindered by the computation in the attention mechanism which involves expensive…

Semantic image segmentation is an important computer vision task that is difficult because it consists of both recognition and segmentation. The task is often cast as a structured output problem on an exponentially large output-space, which…

The objective of this work is to explore how to effectively and efficiently adapt pre-trained visual foundation models to various downstream tasks of semantic segmentation. Previous methods usually fine-tuned the entire networks for each…

Hierarchical clustering is an effective and efficient approach widely used for classical image segmentation methods. However, many existing methods using neural networks generate segmentation masks directly from per-pixel features,…

Transformers have demonstrated remarkable performance in natural language processing and computer vision. However, existing vision Transformers struggle to learn from limited medical data and are unable to generalize on diverse medical…

Semantic segmentation is fundamental to vision systems requiring pixel-level scene understanding, yet deploying it on resource-constrained devices demands efficient architectures. Although existing methods achieve real-time inference…

The emergence of large models, also known as foundation models, has brought significant advancements to AI research. One such model is Segment Anything (SAM), which is designed for image segmentation tasks. However, as with other foundation…

We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder with a 32x compression ratio, which significantly reduces the…