Within the field of instance segmentation, most of the state-of-the-art deep learning networks rely nowadays on cascade architectures [1], where multiple object detectors are trained sequentially, re-sampling the ground truth at each step. This offers a solution to the problem of exponentially vanishing positive samples. However, it also translates into an increase in network complexity in terms of the number of parameters. To address this issue, we propose Recursively Refined R-CNN (R3 -CNN) which avoids duplicates by introducing a loop mechanism instead. At the same time, it achieves a quality boost using a recursive re-sampling technique, where a specific IoU quality is utilized in each recursion to eventually equally cover the positive spectrum. Our experiments highlight the specific encoding of the loop mechanism in the weights, requiring its usage at inference time. The R3 -CNN architecture is able to surpass the recently proposed HTC [4] model, while reducing the number of parameters significantly. Experiments on COCO minival 2017 dataset show performance boost independently from the utilized baseline model. The code is available online at https://github.com/IMPLabUniPr/mmdetection/tree/r3_cnn.

Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing / Rossi, L.; Karimi, A.; Prati, A.. - 13052(2021), pp. 476-486. ((Intervento presentato al convegno 19th International Conference on Computer Analysis of Images and Patterns, CAIP 2021 nel 2021 [10.1007/978-3-030-89128-2_46].

Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing

Rossi L.;Karimi A.;Prati A.
2021

Abstract

Within the field of instance segmentation, most of the state-of-the-art deep learning networks rely nowadays on cascade architectures [1], where multiple object detectors are trained sequentially, re-sampling the ground truth at each step. This offers a solution to the problem of exponentially vanishing positive samples. However, it also translates into an increase in network complexity in terms of the number of parameters. To address this issue, we propose Recursively Refined R-CNN (R3 -CNN) which avoids duplicates by introducing a loop mechanism instead. At the same time, it achieves a quality boost using a recursive re-sampling technique, where a specific IoU quality is utilized in each recursion to eventually equally cover the positive spectrum. Our experiments highlight the specific encoding of the loop mechanism in the weights, requiring its usage at inference time. The R3 -CNN architecture is able to surpass the recently proposed HTC [4] model, while reducing the number of parameters significantly. Experiments on COCO minival 2017 dataset show performance boost independently from the utilized baseline model. The code is available online at https://github.com/IMPLabUniPr/mmdetection/tree/r3_cnn.
978-3-030-89127-5
978-3-030-89128-2
Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing / Rossi, L.; Karimi, A.; Prati, A.. - 13052(2021), pp. 476-486. ((Intervento presentato al convegno 19th International Conference on Computer Analysis of Images and Patterns, CAIP 2021 nel 2021 [10.1007/978-3-030-89128-2_46].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11381/2908453
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact