Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses

• URL: http://arxiv.org/abs/2006.01413v1
• Date: Tue, 2 Jun 2020 06:36:12 GMT
• Title: Resolving Class Imbalance in Object Detection with Weighted Cross Entropy Losses
• Authors: Trong Huy Phan, Kazuma Yamamoto
• Abstract summary: Object detection is an important task in computer vision which serves a lot of real-world applications such as autonomous driving, surveillance and robotics. There are still limitations in performance of detectors when it comes to specialized datasets with uneven object class distributions. We propose to explore and overcome such problem by application of several weighted variants of Cross Entropy loss.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Object detection is an important task in computer vision which serves a lot of real-world applications such as autonomous driving, surveillance and robotics. Along with the rapid thrive of large-scale data, numerous state-of-the-art generalized object detectors (e.g. Faster R-CNN, YOLO, SSD) were developed in the past decade. Despite continual efforts in model modification and improvement in training strategies to boost detection accuracy, there are still limitations in performance of detectors when it comes to specialized datasets with uneven object class distributions. This originates from the common usage of Cross Entropy loss function for object classification sub-task that simply ignores the frequency of appearance of object class during training, and thus results in lower accuracies for object classes with fewer number of samples. Class-imbalance in general machine learning has been widely studied, however, little attention has been paid on the subject of object detection. In this paper, we propose to explore and overcome such problem by application of several weighted variants of Cross Entropy loss, for examples Balanced Cross Entropy, Focal Loss and Class-Balanced Loss Based on Effective Number of Samples to our object detector. Experiments with BDD100K (a highly class-imbalanced driving database acquired from on-vehicle cameras capturing mostly Car-class objects and other minority object classes such as Bus, Person and Motor) have proven better class-wise performances of detector trained with the afore-mentioned loss functions.

Related papers

• Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer [12.042768320132694]
  This paper presents a review of 27 cutting-edge developments in semi-supervised learning for object detection. It covers data augmentation techniques, pseudo-labeling strategies, consistency regularization, and adversarial training methods. We aim to ignite further research interest in overcoming existing challenges and exploring new directions in semi-supervised learning for object detection.
  arXiv  Detail & Related papers  (2024-07-11T12:58:13Z)
• Efficient Meta-Learning Enabled Lightweight Multiscale Few-Shot Object Detection in Remote Sensing Images [15.12889076965307]
  YOLOv7 one-stage detector is subjected to a novel meta-learning training framework. This transformation allows the detector to adeptly address FSOD tasks while capitalizing on its inherent advantage of lightweight. To validate the effectiveness of our proposed detector, we conducted performance comparisons with current state-of-the-art detectors.
  arXiv  Detail & Related papers  (2024-04-29T04:56:52Z)
• OpenNet: Incremental Learning for Autonomous Driving Object Detection with Balanced Loss [3.761247766448379]
  The proposed method can obtain better performance than that of the existing methods. The Experimental results upon the CODA dataset show that the proposed method can obtain better performance than that of the existing methods.
  arXiv  Detail & Related papers  (2023-11-25T06:02:50Z)
• Improved Region Proposal Network for Enhanced Few-Shot Object Detection [23.871860648919593]
  Few-shot object detection (FSOD) methods have emerged as a solution to the limitations of classic object detection approaches. We develop a semi-supervised algorithm to detect and then utilize unlabeled novel objects as positive samples during the FSOD training stage. Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception of the object detection model for large objects.
  arXiv  Detail & Related papers  (2023-08-15T02:35:59Z)
• Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving [91.39625612027386]
  We propose a novel task, called generalized few-shot 3D object detection, where we have a large amount of training data for common (base) objects, but only a few data for rare (novel) classes. Specifically, we analyze in-depth differences between images and point clouds, and then present a practical principle for the few-shot setting in the 3D LiDAR dataset. To solve this task, we propose an incremental fine-tuning method to extend existing 3D detection models to recognize both common and rare objects.
  arXiv  Detail & Related papers  (2023-02-08T07:11:36Z)
• Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning [60.64535309016623]
  We propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector. To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision. We further introduce a incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without catastrophic forgetting.
  arXiv  Detail & Related papers  (2022-05-09T05:08:08Z)
• Class-Aware Robust Adversarial Training for Object Detection [12.600009462416663]
  We present a novel class-aware robust adversarial training paradigm for the object detection task. For a given image, the proposed approach generates an universal adversarial perturbation to simultaneously attack all the occurred objects in the image. The proposed approach decomposes the total loss into class-wise losses and normalizes each class loss using the number of objects for the class.
  arXiv  Detail & Related papers  (2021-03-30T08:02:28Z)
• Closing the Generalization Gap in One-Shot Object Detection [92.82028853413516]
  We show that the key to strong few-shot detection models may not lie in sophisticated metric learning approaches, but instead in scaling the number of categories. Future data annotation efforts should therefore focus on wider datasets and annotate a larger number of categories.
  arXiv  Detail & Related papers  (2020-11-09T09:31:17Z)
• One-Shot Object Detection without Fine-Tuning [62.39210447209698]
  We introduce a two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module. We also propose novel training strategies that effectively improve detection performance. Our method exceeds the state-of-the-art one-shot performance consistently on multiple datasets.
  arXiv  Detail & Related papers  (2020-05-08T01:59:23Z)
• Incremental Few-Shot Object Detection [96.02543873402813]
  OpeN-ended Centre nEt is a detector for incrementally learning to detect class objects with few examples. ONCE fully respects the incremental learning paradigm, with novel class registration requiring only a single forward pass of few-shot training samples.
  arXiv  Detail & Related papers  (2020-03-10T12:56:59Z)
• Stance Detection Benchmark: How Robust Is Your Stance Detection? [65.91772010586605]
  Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim. We introduce a StD benchmark that learns from ten StD datasets of various domains in a multi-dataset learning setting. Within this benchmark setup, we are able to present new state-of-the-art results on five of the datasets.
  arXiv  Detail & Related papers  (2020-01-06T13:37:51Z)

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.