You Only Need End-to-End Training for Long-Tailed Recognition
- URL: http://arxiv.org/abs/2112.05958v3
- Date: Wed, 15 Dec 2021 11:40:54 GMT
- Title: You Only Need End-to-End Training for Long-Tailed Recognition
- Authors: Zhiwei Zhang
- Abstract summary: Cross-entropy loss tends to produce highly correlated features on imbalanced data.
We propose two novel modules, Block-based Relatively Balanced Batch Sampler (B3RS) and Batch Embedded Training (BET)
Experimental results on the long-tailed classification benchmarks, CIFAR-LT and ImageNet-LT, demonstrate the effectiveness of our method.
- Score: 8.789819609485225
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The generalization gap on the long-tailed data sets is largely owing to most
categories only occupying a few training samples. Decoupled training achieves
better performance by training backbone and classifier separately. What causes
the poorer performance of end-to-end model training (e.g., logits margin-based
methods)? In this work, we identify a key factor that affects the learning of
the classifier: the channel-correlated features with low entropy before
inputting into the classifier. From the perspective of information theory, we
analyze why cross-entropy loss tends to produce highly correlated features on
the imbalanced data. In addition, we theoretically analyze and prove its
impacts on the gradients of classifier weights, the condition number of
Hessian, and logits margin-based approach. Therefore, we firstly propose to use
Channel Whitening to decorrelate ("scatter") the classifier's inputs for
decoupling the weight update and reshaping the skewed decision boundary, which
achieves satisfactory results combined with logits margin-based method.
However, when the number of minor classes are large, batch imbalance and more
participation in training cause over-fitting of the major classes. We also
propose two novel modules, Block-based Relatively Balanced Batch Sampler (B3RS)
and Batch Embedded Training (BET) to solve the above problems, which makes the
end-to-end training achieve even better performance than decoupled training.
Experimental results on the long-tailed classification benchmarks, CIFAR-LT and
ImageNet-LT, demonstrate the effectiveness of our method.
Related papers
- Probabilistic Contrastive Learning for Long-Tailed Visual Recognition [78.70453964041718]
Longtailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples.
Recent investigations have revealed that supervised contrastive learning exhibits promising potential in alleviating the data imbalance.
We propose a novel probabilistic contrastive (ProCo) learning algorithm that estimates the data distribution of the samples from each class in the feature space.
arXiv Detail & Related papers (2024-03-11T13:44:49Z) - 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) - Bias Mitigating Few-Shot Class-Incremental Learning [17.185744533050116]
Few-shot class-incremental learning aims at recognizing novel classes continually with limited novel class samples.
Recent methods somewhat alleviate the accuracy imbalance between base and incremental classes by fine-tuning the feature extractor in the incremental sessions.
We propose a novel method to mitigate model bias of the FSCIL problem during training and inference processes.
arXiv Detail & Related papers (2024-02-01T10:37:41Z) - Class Instance Balanced Learning for Long-Tailed Classification [0.0]
Long-tailed image classification task deals with large imbalances in the class frequencies of the training data.
Previous approaches have shown that combining cross-entropy and contrastive learning can improve performance on the long-tailed task.
We propose a novel class instance balanced loss (CIBL), which reweights the relative contributions of a cross-entropy and a contrastive loss as a function of the frequency of class instances in the training batch.
arXiv Detail & Related papers (2023-07-11T15:09:10Z) - Leveraging Angular Information Between Feature and Classifier for
Long-tailed Learning: A Prediction Reformulation Approach [90.77858044524544]
We reformulate the recognition probabilities through included angles without re-balancing the classifier weights.
Inspired by the performance improvement of the predictive form reformulation, we explore the different properties of this angular prediction.
Our method is able to obtain the best performance among peer methods without pretraining on CIFAR10/100-LT and ImageNet-LT.
arXiv Detail & Related papers (2022-12-03T07:52:48Z) - Learning to Re-weight Examples with Optimal Transport for Imbalanced
Classification [74.62203971625173]
Imbalanced data pose challenges for deep learning based classification models.
One of the most widely-used approaches for tackling imbalanced data is re-weighting.
We propose a novel re-weighting method based on optimal transport (OT) from a distributional point of view.
arXiv Detail & Related papers (2022-08-05T01:23:54Z) - Relieving Long-tailed Instance Segmentation via Pairwise Class Balance [85.53585498649252]
Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes.
It causes severe biases of the head classes (with majority samples) against the tailed ones.
We propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences.
arXiv Detail & Related papers (2022-01-08T07:48:36Z) - 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) - The Devil is the Classifier: Investigating Long Tail Relation
Classification with Decoupling Analysis [36.298869931803836]
Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase.
We propose a robust classifier with attentive relation routing, which assigns soft weights by automatically aggregating the relations.
arXiv Detail & Related papers (2020-09-15T12:47:00Z)
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.