Search Results for author: Fehmi Kahraman

Found 3 papers, 2 papers with code

Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation

1 code implementation19 Oct 2021 Kemal Oksuz, Baris Can Cam, Fehmi Kahraman, Zeynep Sonat Baltaci, Sinan Kalkan, Emre Akbas

We present the effectiveness of maIoU on a state-of-the-art (SOTA) assigner, ATSS, by replacing IoU operation by our maIoU and training YOLACT, a SOTA real-time instance segmentation method.

Real-time Instance Segmentation Segmentation +1

Correlation Loss: Enforcing Correlation between Classification and Localization

1 code implementation3 Jan 2023 Fehmi Kahraman, Kemal Oksuz, Sinan Kalkan, Emre Akbas

(ii) Motivated by our observations, e. g., that NMS-free detectors can also benefit from correlation, we propose Correlation Loss, a novel plug-in loss function that improves the performance of various object detectors by directly optimizing correlation coefficients: E. g., Correlation Loss on Sparse R-CNN, an NMS-free method, yields 1. 6 AP gain on COCO and 1. 8 AP gain on Cityscapes dataset.

Classification Inductive Bias +1

Generalized Mask-aware IoU for Anchor Assignment for Real-time Instance Segmentation

no code implementations28 Dec 2023 Barış Can Çam, Kemal Öksüz, Fehmi Kahraman, Zeynep Sonat Baltaci, Sinan Kalkan, Emre Akbaş

This paper introduces Generalized Mask-aware Intersection-over-Union (GmaIoU) as a new measure for positive-negative assignment of anchor boxes during training of instance segmentation methods.

Real-time Instance Segmentation Segmentation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.