Abstract 3D instance segmentation (3DIS) is a crucial task but point-level annotations are
tedious in fully supervised settings. Thus using bounding boxes (bboxes) as annotations has …

Abstract Domain adaptation adapts models to various scenes with different appearances. In
this field active domain adaptation is crucial in effectively sampling a limited number of data …

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

Object detection with weak annotations has attracted much attention recently. Weakly
supervised object detection (WSOD) methods which only use image-level labels to train a …

Weakly-supervised learning has emerged as a compelling method for object detection by
reducing the fully annotated labels requirement in the training procedure. Recently, some …

Generating synthetic data is a promising solution to the challenge of limited training data for
industrial deep learning applications. However, training on synthetic data and testing on real …

Weakly supervised object detection (WSOD) aims to train detectors using only image-
category labels. Current methods typically first generate dense class-agnostic proposals and …

Active learning aims to select the most informative samples for annotation from a large
amount of unlabeled data, in order to reduce time-consuming and labor-intensive manual …

Tongue diagnosis in Traditional Chinese Medicine (TCM) is a crucial diagnostic method that
can reflect an individual's health status. Traditional methods for identifying tooth-marked …

Existing object detection and annotation methods in surveillance systems often suffer from
inefficiencies due to manual labeling and a lack of accurate distance estimation, which limits …