Related papers: Rethinking Query-based Transformer for Continual I…

In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we…

In class-incremental learning, the model is expected to learn new classes continually while maintaining knowledge on previous classes. The challenge here lies in preserving the model's ability to effectively represent prior classes in the…

This paper addresses the unrealistic aspect of the commonly adopted Continuous Incremental Semantic Segmentation (CISS) scenario, termed overlapped. We point out that overlapped allows the same image to reappear in future tasks with…

Amodal Instance Segmentation (AIS) aims to segment the region of both visible and possible occluded parts of an object instance. While Mask R-CNN-based AIS approaches have shown promising results, they are unable to model high-level…

Class-agnostic image segmentation is a crucial component in automating image editing workflows, especially in contexts where object selection traditionally involves interactive tools. Existing methods in the literature often adhere to…

In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are lifelong image classification or recognition of environmental objects during interaction of…

Continual Semantic Segmentation (CSS) seeks to incrementally learn to segment novel classes while preserving knowledge of previously encountered ones. Recent advancements in CSS have been largely driven by the adoption of Pre-trained Vision…

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful…

Two-stage and query-based instance segmentation methods have achieved remarkable results. However, their segmented masks are still very coarse. In this paper, we present Mask Transfiner for high-quality and efficient instance segmentation.…

One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these…

Image segmentation remains a challenging task in computer vision, demanding robust mask generation and precise classification. Recent mask-based approaches yield high-quality masks by capturing global context. However, accurately…

In recent years, instance segmentation has garnered significant attention across various applications. However, training a fully-supervised instance segmentation model requires costly both instance-level and pixel-level annotations. In…

Class-incremental learning (CIL) enables models to continuously learn new categories from sequential tasks without forgetting previously acquired knowledge. While recent advances in vision-language models such as CLIP have demonstrated…

In clinical settings, where acquisition conditions and patient populations change over time, continual learning is key for ensuring the safe use of deep neural networks. Yet most existing work focuses on convolutional architectures and…

Continual video instance segmentation demands both the plasticity to absorb new object categories and the stability to retain previously learned ones, all while preserving temporal consistency across frames. In this work, we introduce…

Prior studies in embodied AI consistently show that robust perception is critical for human-robot interaction, yet deploying high-fidelity visual models on resource-constrained agents remains challenging due to limited on-device computation…

While recent feed-forward 3D reconstruction models provide a strong geometric foundation for scene understanding, extending them to 3D instance segmentation typically relies on a disjointed "lift-and-cluster" paradigm. Grouping dense…

The recent Segment Anything Models (SAMs) have emerged as foundational visual models for general interactive segmentation. Despite demonstrating robust generalization abilities, they still suffer performance degradations in scenarios…

Semantic segmentation involves assigning a specific category to each pixel in an image. While Vision Transformer-based models have made significant progress, current semantic segmentation methods often struggle with precise predictions in…

Referring Image Segmentation (RIS) - the problem of identifying objects in images through natural language sentences - is a challenging task currently mostly solved through supervised learning. However, while collecting referred annotation…