相关论文: Boundary-Refined Prototype Generation: A General E…

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…

Recently, several weakly supervised learning methods have been devoted to utilize bounding box supervision for training deep semantic segmentation models. Most existing methods usually leverage the generic proposal generators (e.g., dense…

Supervised deep learning for semantic segmentation has achieved excellent results in accurately identifying anatomical and pathological structures in medical images. However, it often requires large annotated training datasets, which limits…

Automated semantic segmentation of cell nuclei in microscopic images is crucial for disease diagnosis and tissue microenvironment analysis. Nonetheless, this task presents challenges due to the complexity and heterogeneity of cells. While…

Modern semantic segmentation methods devote much effect to adjusting image feature representations to improve the segmentation performance in various ways, such as architecture design, attention mechnism, etc. However, almost all those…

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…

Virtual brainstorming sessions have become a central component of collaborative problem solving, yet the large volume and uneven distribution of ideas often make it difficult to extract valuable insights efficiently. Manual coding of ideas…

We propose a simple yet effective method to learn to segment new indoor scenes from video frames: State-of-the-art methods trained on one dataset, even as large as the SUNRGB-D dataset, can perform poorly when applied to images that are not…

Existing open-vocabulary 3D semantic segmentation methods typically supervise 3D segmentation models by merging text-aligned features (e.g., CLIP) extracted from multi-view images onto 3D points. However, such approaches treat multi-view…

Source-free domain adaptation has developed rapidly in recent years, where the well-trained source model is adapted to the target domain instead of the source data, offering the potential for privacy concerns and intellectual property…

We introduce ARPG, a novel visual Autoregressive model that enables Randomized Parallel Generation, addressing the inherent limitations of conventional raster-order approaches, which hinder inference efficiency and zero-shot generalization…

Despite great progress in supervised semantic segmentation,a large performance drop is usually observed when deploying the model in the wild. Domain adaptation methods tackle the issue by aligning the source domain and the target domain.…

Semi-supervised learning (SSL) has become a promising direction for medical image segmentation, enabling models to learn from limited labeled data alongside abundant unlabeled samples. However, existing SSL approaches for multi-modal…

End-to-end weakly supervised semantic segmentation aims at optimizing a segmentation model in a single-stage training process based on only image annotations. Existing methods adopt an online-trained classification branch to provide pseudo…

Removing supervision in semantic segmentation is still tricky. Current approaches can deal with common categorical patterns yet resort to multi-stage architectures. We design a novel end-to-end model leveraging local-global patch matching…

The unsupervised text clustering is one of the major tasks in natural language processing (NLP) and remains a difficult and complex problem. Conventional \mbox{methods} generally treat this task using separated steps, including text…

Scaling up the vocabulary of semantic segmentation models is extremely challenging because annotating large-scale mask labels is labour-intensive and time-consuming. Recently, language-guided segmentation models have been proposed to…

Optical character recognition (OCR) systems performance have improved significantly in the deep learning era. This is especially true for handwritten text recognition (HTR), where each author has a unique style, unlike printed text, where…

Self-supervised learning has drawn attention through its effectiveness in learning in-domain representations with no ground-truth annotations; in particular, it is shown that properly designed pretext tasks (e.g., contrastive prediction…

We consider the cross-domain sentiment classification problem, where a sentiment classifier is to be learned from a source domain and to be generalized to a target domain. Our approach explicitly minimizes the distance between the source…