Cognitive vision inspired object segmentation metric and loss function

范登平,; 季葛鹏,; 秦雪彬,; 程明明,

doi:10.1360/ssi-2020-0370

Cited by 73 publications

(4 citation statements)

References 44 publications

(97 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following recommendations from common methods for polyp segmentation [ 21 , 42 ], we utilized mean Dice (

), mean IoU (

), mean absolute error (MAE) [ 54 ], weighted F-measure (

) [ 55 ], S-measure (

) [ 56 ], and mean E-measure (

) [ 57 ] as our assessment indicators for comprehensively investigating our model’s performance. Among these indicators,

and

were regional level similarity measures and mainly highlighted the internal consistency of segmented objects.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Improved dual-aggregation polyp segmentation network combining a pyramid vision transformer with a fully convolutional network

Li,

Huang,

Zhou

et al. 2024

Biomed. Opt. Express

View full text Add to dashboard Cite

Automatic and precise polyp segmentation in colonoscopy images is highly valuable for diagnosis at an early stage and surgery of colorectal cancer. Nevertheless, it still posed a major challenge due to variations in the size and intricate morphological characteristics of polyps coupled with the indistinct demarcation between polyps and mucosas. To alleviate these challenges, we proposed an improved dual-aggregation polyp segmentation network, dubbed Dua-PSNet, for automatic and accurate full-size polyp prediction by combining both the transformer branch and a fully convolutional network (FCN) branch in a parallel style. Concretely, in the transformer branch, we adopted the B3 variant of pyramid vision transformer v2 (PVTv2-B3) as an image encoder for capturing multi-scale global features and modeling long-distant interdependencies between them whilst designing an innovative multi-stage feature aggregation decoder (MFAD) to highlight critical local feature details and effectively integrate them into global features. In the decoder, the adaptive feature aggregation (AFA) block was constructed for fusing high-level feature representations of different scales generated by the PVTv2-B3 encoder in a stepwise adaptive manner for refining global semantic information, while the ResidualBlock module was devised to mine detailed boundary cues disguised in low-level features. With the assistance of the selective global-to-local fusion head (SGLFH) module, the resulting boundary details were aggregated selectively with these global semantic features, strengthening these hierarchical features to cope with scale variations of polyps. The FCN branch embedded in the designed ResidualBlock module was used to encourage extraction of highly merged fine features to match the outputs of the Transformer branch into full-size segmentation maps. In this way, both branches were reciprocally influenced and complemented to enhance the discrimination capability of polyp features and enable a more accurate prediction of a full-size segmentation map. Extensive experiments on five challenging polyp segmentation benchmarks demonstrated that the proposed Dua-PSNet owned powerful learning and generalization ability and advanced the state-of-the-art segmentation performance among existing cutting-edge methods. These excellent results showed our Dua-PSNet had great potential to be a promising solution for practical polyp segmentation tasks in which wide variations of data typically occurred.

show abstract

“…Following recommendations from common methods for polyp segmentation [ 21 , 42 ], we utilized mean Dice (

), mean IoU (

), mean absolute error (MAE) [ 54 ], weighted F-measure (

) [ 55 ], S-measure (

) [ 56 ], and mean E-measure (

) [ 57 ] as our assessment indicators for comprehensively investigating our model’s performance. Among these indicators,

and

were regional level similarity measures and mainly highlighted the internal consistency of segmented objects.…”

Section: Experiments and Resultsmentioning

confidence: 99%

Improved dual-aggregation polyp segmentation network combining a pyramid vision transformer with a fully convolutional network

Li,

Huang,

Zhou

et al. 2024

Biomed. Opt. Express

View full text Add to dashboard Cite

show abstract

“…Please note that the number after each dataset indicates its size. Evaluation Metrics: The widely used evaluation metrics include Mean Absolute Error, Mean F-measure [80], Mean E-measure [81] and S-measure [82] denoted as M, F β , E ξ , S α , respectively. Specifically, the F β and M focus on the local (per-pixel) match between ground truth and prediction, while S α pays attention to the object structure similarities.…”

Section: A Settingsmentioning

confidence: 99%

Predictive Uncertainty Estimation for Camouflaged Object Detection

Zhang

Hamidouche

et al. 2023

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

“…To provide a comprehensive evaluation of the performance, we adopt six universally-agreed metrics, including 1) S-measure (S m ) [49], 2) mean E-measure (E φ ) [50], 3) weighted F-measure (F w β ) [51], 4) mean absolute error (M ), 5)Precision-Recall curves, 6) F-measure curves. Note that for M , a lower value indicates better performance.…”

Section: A Datasets and Evaluation Metricsmentioning

confidence: 99%