Related papers: APSeg: Auto-Prompt Network for Cross-Domain Few-Sh…

Generalized few-shot semantic segmentation (GFSS) aims to segment objects of both base and novel classes, using sufficient samples of base classes and few samples of novel classes. Representative GFSS approaches typically employ a two-phase…

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…

Multimodal image fusion and semantic segmentation are critical for autonomous driving. Despite advancements, current models often struggle with segmenting densely packed elements due to a lack of comprehensive fusion features for guidance…

Cross-Domain Few-Shot Learning has witnessed great stride with the development of meta-learning. However, most existing methods pay more attention to learning domain-adaptive inductive bias (meta-knowledge) through feature-wise manipulation…

Promptable foundation models such as the Segment Anything Model (SAM) produce high-quality masks but remain semantically blind, relying on external prompts to specify categories. Existing vision-language approaches address this limitation…

The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially…

Semantic segmentations of pathological entities have crucial clinical value in computational pathology workflows. Foundation models, such as the Segment Anything Model (SAM), have been recently proposed for universal use in segmentation…

Is Segment Anything Model 3 (SAM3) capable in segmenting Any Pathology Images? Digital pathology segmentation spans tissue-level and nuclei-level scales, where traditional methods often suffer from high annotation costs and poor…

Semantic segmentation is a significant perception task in autonomous driving. It suffers from the risks of adversarial examples. In the past few years, deep learning has gradually transitioned from convolutional neural network (CNN) models…

Zero-shot learning (ZSL) aims at recognizing unseen classes with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space (FS) shared by both seen and unseen classes, i.e., attributes or…

In the semantic segmentation of remote sensing images, acquiring complete ground objects is critical for achieving precise analysis. However, this task is severely hindered by two major challenges: high intra-class variance and high…

Semantic segmentation, vital for applications ranging from autonomous driving to robotics, faces significant challenges in domains where collecting large annotated datasets is difficult or prohibitively expensive. In such contexts, such as…

Leveraging the extensive training data from SA-1B, the Segment Anything Model (SAM) demonstrates remarkable generalization and zero-shot capabilities. However, as a category-agnostic instance segmentation method, SAM heavily relies on prior…

Few-Shot Class-Incremental Learning (FSCIL) models aim to incrementally learn new classes with scarce samples while preserving knowledge of old ones. Existing FSCIL methods usually fine-tune the entire backbone, leading to overfitting and…

In light of the diminishing returns of traditional methods for enhancing transmission rates, the domain of semantic communication presents promising new frontiers. Focusing on image transmission, this paper explores the application of…

Few-shot segmentation (FSS) is a dense prediction task that aims to infer the pixel-wise labels of unseen classes using only a limited number of annotated images. The key challenge in FSS is to classify the labels of query pixels using…

Semantic segmentation is a crucial task in medical imaging. Although supervised learning techniques have proven to be effective in performing this task, they heavily depend on large amounts of annotated training data. The recently…

Segment Anything Model 2 (SAM 2), a prompt-driven foundation model extending SAM to both image and video domains, has shown superior zero-shot performance compared to its predecessor. Building on SAM's success in medical image segmentation,…

Source-free domain adaptation (SFDA) for segmentation aims at adapting a model trained in the source domain to perform well in the target domain with only the source model and unlabeled target data. Inspired by the recent success of Segment…

Deep learning-based medical image segmentation typically requires large amount of labeled data for training, making it less applicable in clinical settings due to high annotation cost. Semi-supervised learning (SSL) has emerged as an…