Search Results for author:
Found 11 papers, 9 papers with code
Localization Recall Precision (LRP): A New Performance Metric for Object Detection
Moreover, we present LRP results of a simple online video object detector which uses a SOTA still image object detector and show that the class-specific optimized thresholds increase the accuracy against the common approach of using a general threshold for all classes.
Imbalance Problems in Object Detection: A Review
In this paper, we present a comprehensive review of the imbalance problems in object detection.
Generating Positive Bounding Boxes for Balanced Training of Object Detectors
Using our generator as an analysis tool, we show that (i) IoU imbalance has an adverse effect on performance, (ii) hard positive example mining improves the performance only for certain input IoU distributions, and (iii) the imbalance among the foreground classes has an adverse effect on performance and that it can be alleviated at the batch level.
Ranked #194 on
Object Detection
on COCO minival
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection.
Ranked #75 on
Object Detection
on COCO test-dev
One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks
Despite being widely used as a performance measure for visual detection tasks, Average Precision (AP) is limited in (i) reflecting localisation quality, (ii) interpretability and (iii) robustness to the design choices regarding its computation, and its applicability to outputs without confidence scores.
Rank & Sort Loss for Object Detection and Instance Segmentation
RS Loss supervises the classifier, a sub-network of these methods, to rank each positive above all negatives as well as to sort positives among themselves with respect to (wrt.)
Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation
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.
Ranked #9 on
Real-time Instance Segmentation
on MSCOCO
Correlation Loss: Enforcing Correlation between Classification and Localization
(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.
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
The current approach for testing the robustness of object detectors suffers from serious deficiencies such as improper methods of performing out-of-distribution detection and using calibration metrics which do not consider both localisation and classification quality.
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
Combining the strengths of many existing predictors to obtain a Mixture of Experts which is superior to its individual components is an effective way to improve the performance without having to develop new architectures or train a model from scratch.
Ranked #1 on
Oriented Object Detection
on DOTA 1.0
Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
Referring Image Segmentation (RIS) - the problem of identifying objects in images through natural language sentences - is a challenging task currently mostly solved through supervised learning.
