IDNet: Information Decomposition Network for Fast Panoptic Segmentation

Lin, Guangchen; Li, Songyuan; Chen, Yifeng; Li, Xi

doi:10.1109/tip.2023.3234499

Cited by 3 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…COCO panoptic dataset: In Table 1, we compare the proposed method with existing panoptic segmentation methods [3,[5][6][7][8][9]14,27] on the COCO panoptic [12] dataset. Table 1 shows the PQ, AP th pan scores of the existing methods, which were obtained from the respective papers.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…In contrast, the proposed method provides remarkable mask results for stuff classes, including tree, fence, window, and wall-brick. ADE20K panoptic dataset: Table 2 compares the proposed method with IDNet [14], MaskFormer [8], Panoptic Segformer [6], YOSO [15], and Mask2Former [9] in terms of PQ and AP th pan on ADE20K. The proposed method achieves the best performance in all metrics.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…On the contrary, we propose a query selection algorithm to extract individual queries from image features using object center information. Also, fast panoptic segmentation networks [5,14,15] are presented. YOSO [15] developed the feature pyramid aggregator for speedup in GPU latency and the separable dynamic decoder for generating panoptic kernels.…”

Section: Related Workmentioning

confidence: 99%

“…YOSO [15] developed the feature pyramid aggregator for speedup in GPU latency and the separable dynamic decoder for generating panoptic kernels. IDNet [14] decomposes panoptic segmentation into category and location information, which simplifies the network architecture.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Center-Guided Transformer for Panoptic Segmentation

Baek,

Lee,

Choo

et al. 2023

Electronics

View full text Add to dashboard Cite

A panoptic segmentation network to predict masks and classes for things and stuff in images is proposed in this work. Recently, panoptic segmentation has been advanced through the combination of the query-based learning and end-to-end learning approaches. Current research focuses on learning queries without distinguishing between thing and stuff classes. We present decoupling query learning to generate effective thing and stuff queries for panoptic segmentation. For this purpose, we adopt different workflows for thing and stuff queries. We design center-guided query selection for thing queries, which focuses on the center regions of individual instances in images, while we set stuff queries as randomly initialized embeddings. Also, we apply a decoupling mask to the self-attention of query features to prevent interactions between things and stuff. In the query selection process, we generate a center heatmap that guides thing query selection. Experimental results demonstrate that the proposed panoptic segmentation network outperforms the state of the art on two panoptic segmentation datasets.

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Center-Guided Transformer for Panoptic Segmentation

Baek,

Lee,

Choo

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

An Improved Shared Encoder-Based Model for Fast Panoptic Segmentation

Ni,

Ren,

Tang

et al. 2024

IEEE Sensors J.

View full text Add to dashboard Cite

Cascade contour-enhanced panoptic segmentation for robotic vision perception

Xu,

Liu,

Zhu

et al. 2024

Front. Neurorobot.

View full text Add to dashboard Cite

Panoptic segmentation plays a crucial role in enabling robots to comprehend their surroundings, providing fine-grained scene understanding information for robots' intelligent tasks. Although existing methods have made some progress, they are prone to fail in areas with weak textures, small objects, etc. Inspired by biological vision research, we propose a cascaded contour-enhanced panoptic segmentation network called CCPSNet, attempting to enhance the discriminability of instances through structural knowledge. To acquire the scene structure, a cascade contour detection stream is designed, which extracts comprehensive scene contours using channel regulation structural perception module and coarse-to-fine cascade strategy. Furthermore, the contour-guided multi-scale feature enhancement stream is developed to boost the discrimination ability for small objects and weak textures. The stream integrates contour information and multi-scale context features through structural-aware feature modulation module and inverse aggregation technique. Experimental results show that our method improves accuracy on the Cityscapes (61.2 PQ) and COCO (43.5 PQ) datasets while also demonstrating robustness in challenging simulated real-world complex scenarios faced by robots, such as dirty cameras and rainy conditions. The proposed network promises to help the robot perceive the real scene. In future work, an unsupervised training strategy for the network could be explored to reduce the training cost.

show abstract

IDNet: Information Decomposition Network for Fast Panoptic Segmentation

Cited by 3 publications

References 42 publications

Center-Guided Transformer for Panoptic Segmentation

Center-Guided Transformer for Panoptic Segmentation

An Improved Shared Encoder-Based Model for Fast Panoptic Segmentation

Cascade contour-enhanced panoptic segmentation for robotic vision perception

Contact Info

Product

Resources

About