Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Features extracted from the self-supervised backbone.

(a) Input image. (b) A channel that is suitable for foreground-background segmentation. (c) A random channel. (d) A promising channel for instance segmentation. (e) A channel suitable for instance segmentation, multiplied by the foreground mask. As shown, instances in the image are distinguishable by their pixel value.

More »

Fig 1 Expand

Fig 2.

Potential appropriateness of channels for intense segmentation.

As depicted in this figure, a specific channel shows promising potential for performing well in the instance segmentation task. These results were analyzed across different instances.

More »

Fig 2 Expand

Fig 3.

Pipelines of discussed deep spectral methods.

(a) Workflow of [18]. An affinity matrix is created using a dot product with features from a self-supervised backbone. Eigenvectors of the Laplacian matrix derived from the affinity matrix are utilized for segmentation tasks. (b) Application of the proposed NCR module on the features from the self-supervised backbone to remove noisy channels. The Fiedler eigenvector is then employed for foreground-background segmentation. (c) Pipeline for instance segmentation. Stable feature map channels are further reduced based on their standard deviation to enhance feature richness. The resulting feature map is multiplied by the foreground mask, and the affinity matrix is created using the BoC metric. Finally, pixels are clustered using the eigenvectors of the Laplacian matrix, resulting in instance segmentation.

More »

Fig 3 Expand

Fig 4.

Visualization of some channels from the self-supervised backbone.

As evident in this figure, lower entropy corresponds to a better representation of objects in images, while higher entropy results in a more unclear representation resembling noise.

More »

Fig 4 Expand

Fig 5.

Influence of DCR on the distinction between instances in YouTube-VIS 2019 dataset.

As depicted by the orange curve, the standard deviation of the channels diminishes while simultaneously, Δ, which represents the average difference between instances, also decreases. Consequently, channels with a higher standard deviation will probably display a more significant average difference between instances.

More »

Fig 5 Expand

Fig 6.

Qualitative results for instance segmentation, when using dot product to create the affinity matrix.

As illustrated, in some channels from the feature map, there are pixels with very high or low values. Using dot product sensitive to these values can lead to incorrect instance segmentation outputs.

More »

Fig 6 Expand

Fig 7.

Comparison of dot product and Bray-Curtis metrics in creating the affinity matrix.

Three pixels belonging to the same instance are selected from the feature maps, and random noise is added to some of their channels. The affinity matrix created by the dot product is unsuitable for our purpose. In contrast, the matrix created by the Bray-Curtis matrix correctly demonstrates the correlation between the three pixels.

More »

Fig 7 Expand

Fig 8.

Evaluation of the NCR module on the YouTube-VIS 2019 dataset.

Results of Fg-Bg segmentation for various values of M. Channels are sorted in ascending order based on their entropy.

More »

Fig 8 Expand

Fig 9.

Evaluation of the NCR module on the PascalVOC 2012 dataset.

Results of Fg-Bg segmentation for different values of M. Channels are arranged in ascending order based on their entropy.

More »

Fig 9 Expand

Table 1.

F-score results for Fg-Bg segmentation, considering different values of M, with and without post-processing.

More »

Table 1 Expand

Fig 10.

Qualitative outcomes of Fg-Bg segmentation on Youtube-VIS 2019 dataset.

As illustrated, Percentages indicate the proportion of channels preserved from NCR. Precise number of channels to be retained varies for each dataset. It is determined during the generation of final masks.

More »

Fig 10 Expand

Table 2.

A comparison of instance segmentation results between different metrics for creating the affinity matrix, with the proposed metric, regarding mIoU on the Youtube-VIS 2019 and OVIS datasets.

More »

Table 2 Expand

Table 3.

Quantitative results for different metrics under varying levels of occlusion in terms of mIoU on the Youtube-VIS 2019 dataset.

More »

Table 3 Expand

Table 4.

Quantitative results for instance segmentation considering different ratio values, in terms of mIoU on the Youtube-VIS 2019 dataset.

More »

Table 4 Expand

Fig 11.

Results of instance segmentation under various occlusion conditions.

Instance segmentation results under varying levels of occlusion, represented by the MBOR value while utilizing different metrics for creating the affinity matrix. The proposed metric, BoC, outperforms other metrics and produces more accurate masks, even in scenarios with heavy occlusions.

More »

Fig 11 Expand

Fig 12.

Results of instance segmentation across different scale ratio levels.

Extracted masks for different metrics on the Youtube-VIS 2019 dataset. A lower value of ratio indicates greater variation in object sizes.

More »

Fig 12 Expand

Table 5.

Quantitative results for different metrics under varying levels of distance between instances are presented in terms of mIoU on the Youtube-VIS 2019 dataset.

More »

Table 5 Expand

Table 6.

Quantitative results for different metrics under varying levels of FG/BG smoothness in terms of mIoU on the Youtube-VIS 2019 dataset.

More »

Table 6 Expand

Fig 13.

Ratio of variance of intra-instance similarity to inter-instance similarity for different similarity metrics.

As depicted in this figure, the BoC metric showed a reduced mR value compared to alternative metrics. This finding confirms that the BoC metric captures intra-instance and inter-instance similarities more effectively than other metrics, thereby enhancing instance segmentation.

More »

Fig 13 Expand

Table 7.

An ablation study to analyze the impact of proposed components on mIoU.

More »

Table 7 Expand

Fig 14.

An visual ablation study to analyze the impact of proposed BoC metric.

More »

Fig 14 Expand