Two-phase training mitigates class imbalance for camera trap image classification with CNNs

• URL: http://arxiv.org/abs/2112.14491v1
• Date: Wed, 29 Dec 2021 10:47:45 GMT
• Title: Two-phase training mitigates class imbalance for camera trap image classification with CNNs
• Authors: Farjad Malik, Simon Wouters, Ruben Cartuyvels, Erfan Ghadery, Marie-Francine Moens
• Abstract summary: We use two-phase training to increase the performance for minority classes. We find that two-phase training based on majority undersampling increases class-specific F1-scores up to 3.0%. We also find that two-phase training outperforms using only oversampling or undersampling by 6.1% in F1-score on average.
• Score: 17.905795249216805
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: By leveraging deep learning to automatically classify camera trap images, ecologists can monitor biodiversity conservation efforts and the effects of climate change on ecosystems more efficiently. Due to the imbalanced class-distribution of camera trap datasets, current models are biased towards the majority classes. As a result, they obtain good performance for a few majority classes but poor performance for many minority classes. We used two-phase training to increase the performance for these minority classes. We trained, next to a baseline model, four models that implemented a different versions of two-phase training on a subset of the highly imbalanced Snapshot Serengeti dataset. Our results suggest that two-phase training can improve performance for many minority classes, with limited loss in performance for the other classes. We find that two-phase training based on majority undersampling increases class-specific F1-scores up to 3.0%. We also find that two-phase training outperforms using only oversampling or undersampling by 6.1% in F1-score on average. Finally, we find that a combination of over- and undersampling leads to a better performance than using them individually.

Related papers

• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation [7.477118370563593]
  Few-shot-learning (FSL) commonly requires a model to identify images (queries) that belong to classes unseen during training. We generate additional test-class samples by combining original samples with suitable train-class samples via a generative image combiner. We obtain averaged features via an augmentor, which leads to more typical representations through the averaging.
  arXiv  Detail & Related papers  (2024-02-28T12:37:30Z)
• Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera Trap Images [2.294014185517203]
  We evaluate recently proposed techniques to address the long-tail visual recognition of animal species in camera trap images. In general, the square-root sampling was the method that most improved the performance for minority classes by around 10%. The proposed approach achieved the best trade-off between the performance of the tail class and the cost of the head classes' accuracy.
  arXiv  Detail & Related papers  (2022-06-24T18:30:26Z)
• GDC- Generalized Distribution Calibration for Few-Shot Learning [5.076419064097734]
  Few shot learning is an important problem in machine learning as large labelled datasets take considerable time and effort to assemble. Most few-shot learning algorithms suffer from one of two limitations- they either require the design of sophisticated models and loss functions, thus hampering interpretability. We propose a Generalized sampling method that learns to estimate few-shot distributions for classification as weighted random variables of all large classes.
  arXiv  Detail & Related papers  (2022-04-11T16:22:53Z)
• Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning [141.35105358670316]
  We study the difference between a na"ively-trained initial-phase model and the oracle model. We propose Class-wise Decorrelation (CwD) that effectively regularizes representations of each class to scatter more uniformly. Our CwD is simple to implement and easy to plug into existing methods.
  arXiv  Detail & Related papers  (2021-12-09T07:20:32Z)
• Sparse MoEs meet Efficient Ensembles [49.313497379189315]
  We study the interplay of two popular classes of such models: ensembles of neural networks and sparse mixture of experts (sparse MoEs) We present Efficient Ensemble of Experts (E$3$), a scalable and simple ensemble of sparse MoEs that takes the best of both classes of models, while using up to 45% fewer FLOPs than a deep ensemble.
  arXiv  Detail & Related papers  (2021-10-07T11:58:35Z)
• eGAN: Unsupervised approach to class imbalance using transfer learning [8.100450025624443]
  Class imbalance is an inherent problem in many machine learning classification tasks. We explore an unsupervised approach to address these imbalances by leveraging transfer learning from pre-trained image classification models to encoder-based Generative Adversarial Network (eGAN) Best result of 0.69 F1-score was obtained on CIFAR-10 classification task with imbalance ratio of 1:2500.
  arXiv  Detail & Related papers  (2021-04-09T02:37:55Z)
• Learning to Fairly Classify the Quality of Wireless Links [0.5352699766206808]
  We propose a new tree-based link quality classifier that meets high performance and fairly classifies the minority class. We compare the tree-based model, to a multilayer perceptron (MLP) non-linear model and two linear models, namely logistic regression (LR) and SVM, on a selected imbalanced dataset. Our study shows that 1) non-linear models perform slightly better than linear models in general, 2) the proposed non-linear tree-based model yields the best performance trade-off considering F1, training time and fairness, and 3) single metric aggregated evaluations based only on accuracy can hide poor,
  arXiv  Detail & Related papers  (2021-02-23T12:23:27Z)
• Few-shot Action Recognition with Prototype-centered Attentive Learning [88.10852114988829]
  Prototype-centered Attentive Learning (PAL) model composed of two novel components. First, a prototype-centered contrastive learning loss is introduced to complement the conventional query-centered learning objective. Second, PAL integrates a attentive hybrid learning mechanism that can minimize the negative impacts of outliers.
  arXiv  Detail & Related papers  (2021-01-20T11:48:12Z)
• Background Splitting: Finding Rare Classes in a Sea of Background [55.03789745276442]
  We focus on the real-world problem of training accurate deep models for image classification of a small number of rare categories. In these scenarios, almost all images belong to the background category in the dataset (>95% of the dataset is background) We demonstrate that both standard fine-tuning approaches and state-of-the-art approaches for training on imbalanced datasets do not produce accurate deep models in the presence of this extreme imbalance.
  arXiv  Detail & Related papers  (2020-08-28T23:05:15Z)
• M2m: Imbalanced Classification via Major-to-minor Translation [79.09018382489506]
  In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue by augmenting less-frequent classes via translating samples from more-frequent classes. Our experimental results on a variety of class-imbalanced datasets show that the proposed method improves the generalization on minority classes significantly compared to other existing re-sampling or re-weighting methods.
  arXiv  Detail & Related papers  (2020-04-01T13:21:17Z)

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.