A pixel-level coarse-to-fine image segmentation labelling algorithm

Abstract

Fine segmentation labelling tasks are time consuming and typically require a great deal of manual labor. This paper presents a novel method for efficiently creating pixel-level fine segmentation labelling that significantly reduces the amount of necessary human labor. The proposed method utilizes easily produced multiple and complementary coarse labels to build a complete fine label via supervised learning. The primary label among the coarse labels is the manual label, which is produced with simple contours or bounding boxes that roughly encompass an object. All others coarse labels are complementary and are generated automatically using existing algorithms. Fine labels can be rapidly created during the supervised learning of such coarse labels. In the experimental study, the proposed technique achieved a fine label IOU (intersection of union) of 92% in segmenting our newly constructed bean field dataset. The proposed method also achieved 95% and 92% mean IOU when tested on publicly available agricultural CVPPP and CWFID datasets, respectively. Our proposed method of segmentation also achieved a mean IOU of 81% when it was tested on our newly constructed paprika disease dataset, which includes multiple categories.

Dual-Channel Semi-Supervised Adversarial Network for Building Segmentation from UAV-Captured Images

“…An intriguing aspect of our investigation was the trade-off between label ratios and the associated labor labeling costs. As mentioned in references [62,63], an increase in the number of labeled samples exhibits a positive correlation with improved model accuracy. However, this improvement comes at the cost of additional expenses and labor-intensive efforts.…”

Quantisation Scale-Spaces

“…Following the same principles as early DPMs, most approaches rely on adding noise in the forward process. Since coarse-to-fine strategies were shown to improve DPMs [24,28], they inspired Lee et al [29] to use blurring with Gaussian convolution instead. Rissanen et al [13] used the equivalence of Gaussian blur to homogeneous diffusion [18] to establish inverse heat dissipation models.…”

HiCDiffusion - diffusion-enhanced, transformer-based prediction of chromatin interactions from DNA sequences

“…However, those are still used primarily for generating new images from text description -and not improving existing ones. That is why we have decided to implement the deblurring diffusion model (Kawar et al, 2022;Ren et al, 2022;Lee et al, 2022) to guide the network to improve the quality of the given heatmap.…”