Pixelwise instance segmentation with a dynamically instantiated network
Semantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-box level. We propose an Instance Segmentation system that produces a segmentatio...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Published: |
Institute of Electrical and Electronics Engineers
2018
|
| _version_ | 1797059301225791488 |
|---|---|
| author | Arnab, A Torr, P |
| author_facet | Arnab, A Torr, P |
| author_sort | Arnab, A |
| collection | OXFORD |
| description | Semantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-box level. We propose an Instance Segmentation system that produces a segmentation map where each pixel is assigned an object class and instance identity label. Most approaches adapt object detectors to produce segments instead of boxes. In contrast, our method is based on an initial semantic segmentation module, which feeds into an instance subnetwork. This subnetwork uses the initial category-level segmentation, along with cues from the output of an object detector, within an end-to-end CRF to predict instances. This part of our model is dynamically instantiated to produce a variable number of instances per image. Our end-to-end approach requires no post-processing and considers the image holistically, instead of processing independent proposals. Therefore, unlike some related work, a pixel cannot belong to multiple instances. Furthermore, far more precise segmentations are achieved, as shown by our substantial improvements at high APr thresholds. |
| first_indexed | 2024-03-06T20:02:15Z |
| format | Conference item |
| id | oxford-uuid:27b5322b-15df-494c-a5b8-d02889315874 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T20:02:15Z |
| publishDate | 2018 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:27b5322b-15df-494c-a5b8-d028893158742022-03-26T12:08:30ZPixelwise instance segmentation with a dynamically instantiated networkConference itemhttp://purl.org/coar/resource_type/c_5794uuid:27b5322b-15df-494c-a5b8-d02889315874Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2018Arnab, ATorr, PSemantic segmentation and object detection research have recently achieved rapid progress. However, the former task has no notion of different instances of the same object, and the latter operates at a coarse, bounding-box level. We propose an Instance Segmentation system that produces a segmentation map where each pixel is assigned an object class and instance identity label. Most approaches adapt object detectors to produce segments instead of boxes. In contrast, our method is based on an initial semantic segmentation module, which feeds into an instance subnetwork. This subnetwork uses the initial category-level segmentation, along with cues from the output of an object detector, within an end-to-end CRF to predict instances. This part of our model is dynamically instantiated to produce a variable number of instances per image. Our end-to-end approach requires no post-processing and considers the image holistically, instead of processing independent proposals. Therefore, unlike some related work, a pixel cannot belong to multiple instances. Furthermore, far more precise segmentations are achieved, as shown by our substantial improvements at high APr thresholds. |
| spellingShingle | Arnab, A Torr, P Pixelwise instance segmentation with a dynamically instantiated network |
| title | Pixelwise instance segmentation with a dynamically instantiated network |
| title_full | Pixelwise instance segmentation with a dynamically instantiated network |
| title_fullStr | Pixelwise instance segmentation with a dynamically instantiated network |
| title_full_unstemmed | Pixelwise instance segmentation with a dynamically instantiated network |
| title_short | Pixelwise instance segmentation with a dynamically instantiated network |
| title_sort | pixelwise instance segmentation with a dynamically instantiated network |
| work_keys_str_mv | AT arnaba pixelwiseinstancesegmentationwithadynamicallyinstantiatednetwork AT torrp pixelwiseinstancesegmentationwithadynamicallyinstantiatednetwork |