Long-tailed Instance Segmentation using Gumbel Optimized Loss
- URL: http://arxiv.org/abs/2207.10936v1
- Date: Fri, 22 Jul 2022 08:20:23 GMT
- Title: Long-tailed Instance Segmentation using Gumbel Optimized Loss
- Authors: Konstantinos Panagiotis Alexandridis, Jiankang Deng, Anh Nguyen and
Shan Luo
- Abstract summary: We develop a Gumbel Optimized Loss (GOL) method for long-tailed detection and segmentation.
GOL significantly outperforms the best state-of-the-art method by 1.1% on AP.
- Score: 29.240427080642
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Major advancements have been made in the field of object detection and
segmentation recently. However, when it comes to rare categories, the
state-of-the-art methods fail to detect them, resulting in a significant
performance gap between rare and frequent categories. In this paper, we
identify that Sigmoid or Softmax functions used in deep detectors are a major
reason for low performance and are sub-optimal for long-tailed detection and
segmentation. To address this, we develop a Gumbel Optimized Loss (GOL), for
long-tailed detection and segmentation. It aligns with the Gumbel distribution
of rare classes in imbalanced datasets, considering the fact that most classes
in long-tailed detection have low expected probability. The proposed GOL
significantly outperforms the best state-of-the-art method by 1.1% on AP , and
boosts the overall segmentation by 9.0% and detection by 8.0%, particularly
improving detection of rare classes by 20.3%, compared to Mask-RCNN, on LVIS
dataset. Code available at: https://github.com/kostas1515/GOL
Related papers
- The object detection model uses combined extraction with KNN and RF classification [0.0]
This study contributes to the field of object detection with a new approach combining GLCM and LBP as feature vectors as well as VE for classification.
System testing used a dataset of 4,437 2D images, the results for KNN accuracy were 92.7% and F1-score 92.5%, while RF performance was lower.
arXiv Detail & Related papers (2024-05-09T05:21:42Z) - Characterizing the Optimal 0-1 Loss for Multi-class Classification with
a Test-time Attacker [57.49330031751386]
We find achievable information-theoretic lower bounds on loss in the presence of a test-time attacker for multi-class classifiers on any discrete dataset.
We provide a general framework for finding the optimal 0-1 loss that revolves around the construction of a conflict hypergraph from the data and adversarial constraints.
arXiv Detail & Related papers (2023-02-21T15:17:13Z) - Long-tail Detection with Effective Class-Margins [4.18804572788063]
We show how the commonly used mean average precision evaluation metric on an unknown test set is bound by a margin-based binary classification error.
We optimize margin-based binary classification error with a novel surrogate objective called text-Effective Class-Margin Loss (ECM)
arXiv Detail & Related papers (2023-01-23T21:25:24Z) - Precise Location Matching Improves Dense Contrastive Learning in Digital
Pathology [28.62539784951823]
We propose a precise location-based matching mechanism to precisely match regions in two augmentations.
Our method outperforms previous dense matching methods by up to 7.2% in average precision for detection and 5.6% in average precision for instance segmentation tasks.
arXiv Detail & Related papers (2022-12-23T02:11:27Z) - Interclass Prototype Relation for Few-Shot Segmentation [0.0]
With few-shot segmentation, the target class data distribution in the feature space is sparse and has low coverage because of the slight variations in the sample data.
This study proposes the Interclass Prototype Relation Network (IPRNet) which improves the separation performance by reducing the similarity between other classes.
arXiv Detail & Related papers (2022-11-16T05:27:52Z) - CvS: Classification via Segmentation For Small Datasets [52.821178654631254]
This paper presents CvS, a cost-effective classifier for small datasets that derives the classification labels from predicting the segmentation maps.
We evaluate the effectiveness of our framework on diverse problems showing that CvS is able to achieve much higher classification results compared to previous methods when given only a handful of examples.
arXiv Detail & Related papers (2021-10-29T18:41:15Z) - Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance
Segmentation [75.93960390191262]
We exploit prior knowledge of the relations among object categories to cluster fine-grained classes into coarser parent classes.
We propose a simple yet effective resampling method, NMS Resampling, to re-balance the data distribution.
Our method, termed as Forest R-CNN, can serve as a plug-and-play module being applied to most object recognition models.
arXiv Detail & Related papers (2020-08-13T03:52:37Z) - The Devil is in Classification: A Simple Framework for Long-tail Object
Detection and Instance Segmentation [93.17367076148348]
We investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset.
We unveil that a major cause is the inaccurate classification of object proposals.
We propose a simple calibration framework to more effectively alleviate classification head bias with a bi-level class balanced sampling approach.
arXiv Detail & Related papers (2020-07-23T12:49:07Z) - Overcoming Classifier Imbalance for Long-tail Object Detection with
Balanced Group Softmax [88.11979569564427]
We provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution.
We propose a novel balanced group softmax (BAGS) module for balancing the classifiers within the detection frameworks through group-wise training.
Extensive experiments on the very recent long-tail large vocabulary object recognition benchmark LVIS show that our proposed BAGS significantly improves the performance of detectors.
arXiv Detail & Related papers (2020-06-18T10:24:26Z) - Equalization Loss for Long-Tailed Object Recognition [109.91045951333835]
State-of-the-art object detection methods still perform poorly on large vocabulary and long-tailed datasets.
We propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories.
Our method achieves AP gains of 4.1% and 4.8% for the rare and common categories on the challenging LVIS benchmark.
arXiv Detail & Related papers (2020-03-11T09:14:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.