Rethinking Click Embedding for Deep Interactive Image Segmentation

Ding, Zongyuan; Wang, Tao; Sun, Quansen; Chen, Fuhua

doi:10.1109/tii.2022.3157319

Cited by 5 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…c=1 are only fused to the input points, user intention in the click guidance can be diluted as the network layer goes deeper (Zhang et al 2019;Ding et al 2022;Hao et al 2021). Furthermore, the point-based detectors with downsampling layers for computational efficiency may cause potential losses of foreground points or critical information for 3D scene understanding (Hu et al 2021;Zhang et al 2022).…”

Section: Dense Click Guidance (Dcg) If the User Click Encodingmentioning

confidence: 99%

iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Clouds

Choi,

Cho,

Kim

et al. 2024

AAAI

View full text Add to dashboard Cite

Accurately annotating multiple 3D objects in LiDAR scenes is laborious and challenging. While a few previous studies have attempted to leverage semi-automatic methods for cost-effective bounding box annotation, such methods have limitations in efficiently handling numerous multi-class objects. To effectively accelerate 3D annotation pipelines, we propose iDet3D, an efficient interactive 3D object detector. Supporting a user-friendly 2D interface, which can ease the cognitive burden of exploring 3D space to provide click interactions, iDet3D enables users to annotate the entire objects in each scene with minimal interactions. Taking the sparse nature of 3D point clouds into account, we design a negative click simulation (NCS) to improve accuracy by reducing false-positive predictions. In addition, iDet3D incorporates two click propagation techniques to take full advantage of user interactions: (1) dense click guidance (DCG) for keeping user-provided information throughout the network and (2) spatial click propagation (SCP) for detecting other instances of the same class based on the user-specified objects. Through our extensive experiments, we present that our method can construct precise annotations in a few clicks, which shows the practicality as an efficient annotation tool for 3D object detection.

show abstract

Section: Dense Click Guidance (Dcg) If the User Click Encodingmentioning

confidence: 99%

iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Clouds

Choi,

Cho,

Kim

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…After the preprocessing step of extreme clicks, the input consists of RGB cropped images containing objects plus their extreme points. The feature backpropagating refinement scheme (F-BRS) method [ 5 , 6 ] proposes an improved scheme of feature backpropagation that reframes the parameter optimization problem, which runs forward and backward passes through a part of the network, namely the last few layers. The method introduces a set of auxiliary parameters for optimization, which can be optimized without computing and passing backwards through the entire network, making it more efficient.…”

Section: Introductionmentioning

confidence: 99%

An Interactive Image Segmentation Method Based on Multi-Level Semantic Fusion

Zou

Wang

Wen

et al. 2023

Sensors

View full text Add to dashboard Cite

Understanding and analyzing 2D/3D sensor data is crucial for a wide range of machine learning-based applications, including object detection, scene segmentation, and salient object detection. In this context, interactive object segmentation is a vital task in image editing and medical diagnosis, involving the accurate separation of the target object from its background based on user annotation information. However, existing interactive object segmentation methods struggle to effectively leverage such information to guide object-segmentation models. To address these challenges, this paper proposes an interactive image-segmentation technique for static images based on multi-level semantic fusion. Our method utilizes user-guidance information both inside and outside the target object to segment it from the static image, making it applicable to both 2D and 3D sensor data. The proposed method introduces a cross-stage feature aggregation module, enabling the effective propagation of multi-scale features from previous stages to the current stage. This mechanism prevents the loss of semantic information caused by multiple upsampling and downsampling of the network, allowing the current stage to make better use of semantic information from the previous stage. Additionally, we incorporate a feature channel attention mechanism to address the issue of rough network segmentation edges. This mechanism captures richer feature details from the feature channel level, leading to finer segmentation edges. In the experimental evaluation conducted on the PASCAL Visual Object Classes (VOC) 2012 dataset, our proposed interactive image segmentation method based on multi-level semantic fusion demonstrates an intersection over union (IOU) accuracy approximately 2.1% higher than the currently popular interactive image segmentation method in static images. The comparative analysis highlights the improved performance and effectiveness of our method. Furthermore, our method exhibits potential applications in various fields, including medical imaging and robotics. Its compatibility with other machine learning methods for visual semantic analysis allows for integration into existing workflows. These aspects emphasize the significance of our contributions in advancing interactive image-segmentation techniques and their practical utility in real-world applications.

show abstract