Related papers: Diffusion-Driven Two-Stage Active Learning for Low…
As research interests in medical image analysis become increasingly fine-grained, the cost for extensive annotation also rises. One feasible way to reduce the cost is to annotate with coarse-grained superclass labels while using limited…
Open-vocabulary semantic segmentation aims at segmenting arbitrary categories expressed in textual form. Previous works have trained over large amounts of image-caption pairs to enforce pixel-level multimodal alignments. However, captions…
Most contemporary robots have depth sensors, and research on semantic segmentation with RGBD images has shown that depth images boost the accuracy of segmentation. Since it is time-consuming to annotate images with semantic labels per…
Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…
Panoptic and instance segmentation networks are often trained with specialized object detection modules, complex loss functions, and ad-hoc post-processing steps to manage the permutation-invariance of the instance masks. This work builds…
Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…
Deep neural networks (DNNs) have demonstrated exceptional performance across various image segmentation tasks. However, the process of preparing datasets for training segmentation DNNs is both labor-intensive and costly, as it typically…
In multi-domain learning (MDL) scenarios, high labeling effort is required due to the complexity of collecting data from various domains. Active Learning (AL) presents an encouraging solution to this issue by annotating a smaller number of…
Rich high-quality annotated data is critical for semantic segmentation learning, yet acquiring dense and pixel-wise ground-truth is both labor- and time-consuming. Coarse annotations (e.g., scribbles, coarse polygons) offer an economical…
The evolution of semantic segmentation has long been dominated by learning more discriminative image representations for classifying each pixel. Despite the prominent advancements, the priors of segmentation masks themselves, e.g.,…
For best performance, today's semantic segmentation methods use large and carefully labeled datasets, requiring expensive annotation budgets. In this work, we show that coarse annotation is a low-cost but highly effective alternative for…
Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…
Deep Neural Networks (DNNs) have recently shown state of the art performance on semantic segmentation tasks, however, they still suffer from problems of poor boundary localization and spatial fragmented predictions. The difficulties lie in…
The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class…
The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations. However, even the largest public datasets only provide samples with pixel-level annotations for rather limited…
Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from the usage of class priors, which only provide coarse and…
The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two…
We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality. We use score distillation to…
Despite the great progress made by deep neural networks in the semantic segmentation task, traditional neural-networkbased methods typically suffer from a shortage of large amounts of pixel-level annotations. Recent progress in fewshot…
We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the…