加权
残余物
人工智能
计算机科学
透视图(图形)
编码(集合论)
面子(社会学概念)
模式识别(心理学)
班级(哲学)
面部识别系统
空格(标点符号)
采样(信号处理)
机器学习
算法
计算机视觉
集合(抽象数据类型)
滤波器(信号处理)
操作系统
放射科
社会学
医学
社会科学
程序设计语言
作者
Jiequan Cui,Shu Liu,Zhuotao Tian,Zhisheng Zhong,Jiaya Jia
标识
DOI:10.1109/tpami.2022.3174892
摘要
Deep learning algorithms face great challenges with long-tailed data distribution which, however, is quite a common case in real-world scenarios. Previous methods tackle the problem from either the aspect of input space (re-sampling classes with different frequencies) or loss space (re-weighting classes with different weights), suffering from heavy over-fitting to tail classes or hard optimization during training. To alleviate these issues, we propose a more fundamental perspective for long-tailed recognition, i.e., from the aspect of parameter space, and aims to preserve specific capacity for classes with low frequencies. From this perspective, the trivial solution utilizes different branches for the head, medium, tail classes respectively, and then sums their outputs as the final results is not feasible. Instead, we design the effective residual fusion mechanism - with one main branch optimized to recognize images from all classes, another two residual branches are gradually fused and optimized to enhance images from medium+tail classes and tail classes respectively. Then the branches are aggregated into final results by additive shortcuts. We test our method on several benchmarks, i.e., long-tailed version of CIFAR-10, CIFAR-100, Places, ImageNet, and iNaturalist 2018. Experimental results manifest the effectiveness of our method. Our code is available at https://github.com/jiequancui/ResLT.
科研通智能强力驱动
Strongly Powered by AbleSci AI