Self-training methods have gained significant attention in recent years due to their
effectiveness in leveraging small labeled datasets and large unlabeled observations for …

In this paper, we introduce a novel learning scheme named weakly semi-supervised
instance segmentation (WSSIS) with point labels for budget-efficient and high-performance …

Accurate extraction of rooftop photovoltaic from high-resolution remote sensing imagery is
pivotal for propelling green energy planning and development. Conventional deep learning …

Abstract We propose Mask Auto-Labeler (MAL), a high-quality Transformer-based mask
auto-labeling framework for instance segmentation using only box annotations. MAL takes …

This paper introduces a novel approach to learning instance segmentation using extreme
points ie the topmost leftmost bottommost and rightmost points of each object. These points …

Semantic segmentation has achieved huge progress via adopting deep Fully Convolutional
Networks (FCN). However, the performance of FCN-based models severely rely on the …

Weakly supervised segmentation methods have garnered considerable attention due to
their potential to alleviate the need for labor-intensive pixel-level annotations during model …

Weakly-supervised visual recognition using inexact supervision is a critical yet challenging
learning problem. It significantly reduces human labeling costs and traditionally relies on …

Weakly-supervised segmentation with label-efficient sparse annotations has attracted
increasing research attention to reduce the cost of laborious pixel-wise labeling process …

Camouflaged instance segmentation (CIS) aims to detect and segment objects blending
with their surroundings. While existing CIS methods rely heavily on fully-supervised training …