Calibrating Class Activation Maps for Long-Tailed Visual Recognition
Real-world visual recognition problems often exhibit long-tailed distributions, where the amount of data for learning in different categories shows significant imbalance. Standard classification models learned on such data distribution often make biased predictions towards the head classes while generalizing poorly to the tail classes. In this paper, we present two effective modifications of CNNs to improve network learning from long-tailed distribution. First, we present a Class Activation Map Calibration (CAMC) module to improve the learning and prediction of network classifiers, by enforcing network prediction based on important image regions. The proposed CAMC module highlights the correlated image regions across data and reinforces the representations in these areas to obtain a better global representation for classification. Furthermore, we investigate the use of normalized classifiers for representation learning in long-tailed problems. Our empirical study demonstrates that by simply scaling the outputs of the classifier with an appropriate scalar, we can effectively improve the classification accuracy on tail classes without losing the accuracy of head classes. We conduct extensive experiments to validate the effectiveness of our design and we set new state-of-the-art performance on five benchmarks, including ImageNet-LT, Places-LT, iNaturalist 2018, CIFAR10-LT, and CIFAR100-LT.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
Balancing Domain Experts for Long-Tailed Camera-Trap Recognition
Label distributions in camera-trap images are highly imbalanced and long-tailed, resulting in neural networks tending to be biased towards head-classes that appear frequently. Although long-tail learning has been extreme…
Long-tail LearningOptical Flow EstimationSFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation
Image-level weakly supervised semantic segmentation has received increasing attention due to its low annotation cost. Existing methods mainly rely on Class Activation Mapping (CAM) to obtain pseudo-labels for training se…
Pseudo LabelSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1Calibrating CNNs for Lifelong Learning
We present an approach for lifelong/continual learning of convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when moving from one task to the other. We show that the acti…
Continual LearningLifelong learningFeature Space Augmentation for Long-Tailed Data
Real-world data often follow a long-tailed distribution as the frequency of each class is typically different. For example, a dataset can have a large number of under-represented classes and a few classes with more than …
Image ClassificationLong-tail LearningBag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks
In recent years, visual recognition on challenging long-tailed distributions, where classes often exhibit extremely imbalanced frequencies, has made great progress mostly based on various complex paradigms (e.g., meta le…
Data AugmentationMeta-Learning