ResLT: Residual Learning for Long-tailed Recognition

• URL: http://arxiv.org/abs/2101.10633v2
• Date: Wed, 27 Jan 2021 01:30:23 GMT
• Title: ResLT: Residual Learning for Long-tailed Recognition
• Authors: Jiequan Cui, Shu Liu, Zhuotao Tian, Zhisheng Zhong, Jiaya Jia
• Abstract summary: We propose a more fundamental perspective for long-tailed recognition, i.e., from the aspect of parameter space. 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. We test our method on several benchmarks, i.e., long-tailed version of CIFAR-10, CIFAR-100, Places, ImageNet, and iNaturalist 2018.
• Score: 64.19728932445523
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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 that our method achieves new state-of-the-art for long-tailed recognition. Code will be available at \url{https://github.com/FPNAS/ResLT}.

Related papers

• Deep Feature Surgery: Towards Accurate and Efficient Multi-Exit Networks [13.492494712188922]
  This paper introduces Deep Feature Surgery (methodname) to resolve gradient conflict issues during the training of multi-exit networks. methodnamereduces the training operations with the reduced complexity of backpropagation. Budgeted batch classification evaluation shows that DFS uses about $symbolmathbf2boldtimes$ fewer average FLOPs per image to achieve the same classification accuracy as baseline methods on Cifar100.
  arXiv  Detail & Related papers  (2024-07-19T02:31:31Z)
• LCReg: Long-Tailed Image Classification with Latent Categories based Recognition [81.5551335554507]
  We propose the Latent Categories based long-tail Recognition (LCReg) method. Our hypothesis is that common latent features shared by head and tail classes can be used to improve feature representation. Specifically, we learn a set of class-agnostic latent features shared by both head and tail classes, and then use semantic data augmentation on the latent features to implicitly increase the diversity of the training sample.
  arXiv  Detail & Related papers  (2023-09-13T02:03:17Z)
• Constructing Balance from Imbalance for Long-tailed Image Recognition [50.6210415377178]
  The imbalance between majority (head) classes and minority (tail) classes severely skews the data-driven deep neural networks. Previous methods tackle with data imbalance from the viewpoints of data distribution, feature space, and model design. We propose a concise paradigm by progressively adjusting label space and dividing the head classes and tail classes. Our proposed model also provides a feature evaluation method and paves the way for long-tailed feature learning.
  arXiv  Detail & Related papers  (2022-08-04T10:22:24Z)
• Feature Generation for Long-tail Classification [36.186909933006675]
  We show how to generate meaningful features by estimating the tail category's distribution. We also present a qualitative analysis of generated features using t-SNE visualizations and analyze the nearest neighbors used to calibrate the tail class distributions.
  arXiv  Detail & Related papers  (2021-11-10T21:34:29Z)
• Distributional Robustness Loss for Long-tail Learning [20.800627115140465]
  Real-world data is often unbalanced and long-tailed, but deep models struggle to recognize rare classes in the presence of frequent classes. We show that the feature extractor part of deep networks suffers greatly from this bias. We propose a new loss based on robustness theory, which encourages the model to learn high-quality representations for both head and tail classes.
  arXiv  Detail & Related papers  (2021-04-07T11:34:04Z)
• Improving Calibration for Long-Tailed Recognition [68.32848696795519]
  We propose two methods to improve calibration and performance in such scenarios. For dataset bias due to different samplers, we propose shifted batch normalization. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-01T13:55:21Z)
• Long-tailed Recognition by Routing Diverse Distribution-Aware Experts [64.71102030006422]
  We propose a new long-tailed classifier called RoutIng Diverse Experts (RIDE) It reduces the model variance with multiple experts, reduces the model bias with a distribution-aware diversity loss, reduces the computational cost with a dynamic expert routing module. RIDE outperforms the state-of-the-art by 5% to 7% on CIFAR100-LT, ImageNet-LT and iNaturalist 2018 benchmarks.
  arXiv  Detail & Related papers  (2020-10-05T06:53:44Z)
• SCAN: Learning to Classify Images without Labels [73.69513783788622]
  We advocate a two-step approach where feature learning and clustering are decoupled. A self-supervised task from representation learning is employed to obtain semantically meaningful features. We obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime.
  arXiv  Detail & Related papers  (2020-05-25T18:12:33Z)

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.