Open Long-Tailed Recognition in a Dynamic World

• URL: http://arxiv.org/abs/2208.08349v1
• Date: Wed, 17 Aug 2022 15:22:20 GMT
• Title: Open Long-Tailed Recognition in a Dynamic World
• Authors: Ziwei Liu, Zhongqi Miao, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu
• Abstract summary: Real world data often exhibits a long-tailed and open-ended (with unseen classes) distribution. A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and acknowledge novelty upon the instances of unseen classes (open classes) We define Open Long-Tailed Recognition++ as learning from such naturally distributed data and optimizing for the classification accuracy over a balanced test set.
• Score: 82.91025831618545
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Real world data often exhibits a long-tailed and open-ended (with unseen classes) distribution. A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and acknowledge novelty upon the instances of unseen classes (open classes). We define Open Long-Tailed Recognition++ (OLTR++) as learning from such naturally distributed data and optimizing for the classification accuracy over a balanced test set which includes both known and open classes. OLTR++ handles imbalanced classification, few-shot learning, open-set recognition, and active learning in one integrated algorithm, whereas existing classification approaches often focus only on one or two aspects and deliver poorly over the entire spectrum. The key challenges are: 1) how to share visual knowledge between head and tail classes, 2) how to reduce confusion between tail and open classes, and 3) how to actively explore open classes with learned knowledge. Our algorithm, OLTR++, maps images to a feature space such that visual concepts can relate to each other through a memory association mechanism and a learned metric (dynamic meta-embedding) that both respects the closed world classification of seen classes and acknowledges the novelty of open classes. Additionally, we propose an active learning scheme based on visual memory, which learns to recognize open classes in a data-efficient manner for future expansions. On three large-scale open long-tailed datasets we curated from ImageNet (object-centric), Places (scene-centric), and MS1M (face-centric) data, as well as three standard benchmarks (CIFAR-10-LT, CIFAR-100-LT, and iNaturalist-18), our approach, as a unified framework, consistently demonstrates competitive performance. Notably, our approach also shows strong potential for the active exploration of open classes and the fairness analysis of minority groups.

Related papers

• Robust Semi-Supervised Learning for Self-learning Open-World Classes [5.714673612282175]
  In real-world applications, unlabeled data always contain classes not present in the labeled set. We propose an open-world SSL method for Self-learning Open-world Classes (SSOC), which can explicitly self-learn multiple unknown classes. SSOC outperforms the state-of-the-art baselines on multiple popular classification benchmarks.
  arXiv  Detail & Related papers  (2024-01-15T09:27:46Z)
• Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation [68.13453771001522]
  We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings. We conduct extensive experiments and evaluate our model on large-scale real-world data.
  arXiv  Detail & Related papers  (2023-06-14T13:07:48Z)
• Bayesian Embeddings for Few-Shot Open World Recognition [60.39866770427436]
  We extend embedding-based few-shot learning algorithms to the open-world recognition setting. We benchmark our framework on open-world extensions of the common MiniImageNet and TieredImageNet few-shot learning datasets.
  arXiv  Detail & Related papers  (2021-07-29T00:38:47Z)
• Distribution Alignment: A Unified Framework for Long-tail Visual Recognition [52.36728157779307]
  We propose a unified distribution alignment strategy for long-tail visual recognition. We then introduce a generalized re-weight method in the two-stage learning to balance the class prior. Our approach achieves the state-of-the-art results across all four recognition tasks with a simple and unified framework.
  arXiv  Detail & Related papers  (2021-03-30T14:09:53Z)
• Open-World Semi-Supervised Learning [66.90703597468377]
  We introduce a new open-world semi-supervised learning setting in which the model is required to recognize previously seen classes. We propose ORCA, an approach that learns to simultaneously classify and cluster the data. We demonstrate that ORCA accurately discovers novel classes and assigns samples to previously seen classes on benchmark image classification datasets.
  arXiv  Detail & Related papers  (2021-02-06T07:11:07Z)
• CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition [52.66360172784038]
  We propose a clustering-based model, which considers all training samples at once, instead of optimizing for each instance individually. We call the proposed method CLASTER and observe that it consistently improves over the state-of-the-art in all standard datasets.
  arXiv  Detail & Related papers  (2021-01-18T12:46:24Z)
• Boosting Deep Open World Recognition by Clustering [37.5993398894786]
  We show how we can boost the performance of deep open world recognition algorithms by means of a new loss formulation. We propose a strategy to learn class-specific rejection thresholds, instead of estimating a single global threshold. Experiments on RGB-D Object and Core50 show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-20T12:07:39Z)

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.