Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation
Dichotomous Image Segmentation (DIS) tasks require highly precise annotations, and
traditional dataset creation methods are labor intensive, costly, and require extensive …
traditional dataset creation methods are labor intensive, costly, and require extensive …
Multi-view Aggregation Network for Dichotomous Image Segmentation
Abstract Dichotomous Image Segmentation (DIS) has recently emerged towards high-
precision object segmentation from high-resolution natural images. When designing an …
precision object segmentation from high-resolution natural images. When designing an …
Segment anything with precise interaction
Although the Segment Anything Model (SAM) has achieved impressive results in many
segmentation tasks and benchmarks, its performance noticeably deteriorates when applied …
segmentation tasks and benchmarks, its performance noticeably deteriorates when applied …
Boundary-aware dichotomous image segmentation
H Tang, S Chen, Y Liu, S Wang, Z Chen, X Hu - The Visual Computer, 2024 - Springer
Abstract Dichotomous Image Segmentation is a category-agnostic task aims to segment
highly accurate objects from natural images. In semantic segmentation tasks, the utilization …
highly accurate objects from natural images. In semantic segmentation tasks, the utilization …
Bilateral Reference for High-Resolution Dichotomous Image Segmentation
We introduce a novel bilateral reference framework (*** BiRefNet***) for high-resolution
dichotomous image segmentation (DIS). It comprises two essential components: the …
dichotomous image segmentation (DIS). It comprises two essential components: the …
High-Precision Dichotomous Image Segmentation With Frequency and Scale Awareness
Dichotomous image segmentation (DIS) with rich fine-grained details within a single image
is a challenging task. Despite the plausible results achieved by deep learning-based …
is a challenging task. Despite the plausible results achieved by deep learning-based …
Evaluation Study on SAM 2 for Class-agnostic Instance-level Segmentation
Segment Anything Model (SAM) has demonstrated powerful zero-shot segmentation
performance in natural scenes. The recently released Segment Anything Model 2 (SAM2) …
performance in natural scenes. The recently released Segment Anything Model 2 (SAM2) …
Cross-Domain Facial Expression Recognition by Combining Transfer Learning and Face-Cycle Generative Adversarial Network
Y Zhou, B Yang, Z Liu, Q Wang, P Xiong - Multimedia Tools and …, 2024 - Springer
Facial expression recognition (FER) is one of the important research topics in computer
vision. It is difficult to obtain high accuracy in FER tasks, especially when the high-quality …
vision. It is difficult to obtain high accuracy in FER tasks, especially when the high-quality …
Robot Manipulation in Salient Vision through Referring Image Segmentation and Geometric Constraints
C Jiang, A Luo, M Jagersand - arXiv preprint arXiv:2409.11518, 2024 - arxiv.org
In this paper, we perform robot manipulation activities in real-world environments with
language contexts by integrating a compact referring image segmentation model into the …
language contexts by integrating a compact referring image segmentation model into the …