paper-with-me

Papers

Calibrating Class Activation Maps for Long-Tailed Visual Recognition

2021-08-29 · Chi Zhang, Guosheng Lin, Lvlong Lai, Henghui Ding, Qingyao Wu

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.

📄 PDF Abstract BibTeX arXiv:2108.12757

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Balancing Domain Experts for Long-Tailed Camera-Trap Recognition

2022-02-15 · Byeongjun Park, JeongSoo Kim, Seungju Cho, Heeseon Kim 외

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 Estimation

SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation

2024-01-22 · Xinqiao Zhao, Feilong Tang, Xiaoyang Wang, Jimin Xiao

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+1

Calibrating CNNs for Lifelong Learning

2020-12-01 · NeurIPS 2020 12 · Pravendra Singh, Vinay Kumar Verma, Pratik Mazumder, Lawrence Carin 외

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 learning

Feature Space Augmentation for Long-Tailed Data

2020-08-09 · ECCV 2020 8 · Peng Chu, Xiao Bian, Shaopeng Liu, Haibin Ling

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 Learning

Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks

2021-05-19 · Association for the Advancement of Artificial Intelligence 2021 5 · Yongshun Zhang, Xiu-Shen Wei, Boyan Zhou, Jianxin Wu

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