Learning with an Evolving Class Ontology

• URL: http://arxiv.org/abs/2210.04993v2
• Date: Wed, 12 Oct 2022 04:05:37 GMT
• Title: Learning with an Evolving Class Ontology
• Authors: Zhiqiu Lin, Deepak Pathak, Yu-Xiong Wang, Deva Ramanan, Shu Kong
• Abstract summary: Lifelong learners must recognize concept that evolve over time. A common yet underexplored scenario is learning with labels over time that refine/expand old classes.
• Score: 82.89062737922869
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lifelong learners must recognize concept vocabularies that evolve over time. A common yet underexplored scenario is learning with class labels over time that refine/expand old classes. For example, humans learn to recognize ${\tt dog}$ before dog breeds. In practical settings, dataset $\textit{versioning}$ often introduces refinement to ontologies, such as autonomous vehicle benchmarks that refine a previous ${\tt vehicle}$ class into ${\tt school-bus}$ as autonomous operations expand to new cities. This paper formalizes a protocol for studying the problem of $\textit{Learning with Evolving Class Ontology}$ (LECO). LECO requires learning classifiers in distinct time periods (TPs); each TP introduces a new ontology of "fine" labels that refines old ontologies of "coarse" labels (e.g., dog breeds that refine the previous ${\tt dog}$). LECO explores such questions as whether to annotate new data or relabel the old, how to leverage coarse labels, and whether to finetune the previous TP's model or train from scratch. To answer these questions, we leverage insights from related problems such as class-incremental learning. We validate them under the LECO protocol through the lens of image classification (CIFAR and iNaturalist) and semantic segmentation (Mapillary). Our experiments lead to surprising conclusions; while the current status quo is to relabel existing datasets with new ontologies (such as COCO-to-LVIS or Mapillary1.2-to-2.0), LECO demonstrates that a far better strategy is to annotate $\textit{new}$ data with the new ontology. However, this produces an aggregate dataset with inconsistent old-vs-new labels, complicating learning. To address this challenge, we adopt methods from semi-supervised and partial-label learning. Such strategies can surprisingly be made near-optimal, approaching an "oracle" that learns on the aggregate dataset exhaustively labeled with the newest ontology.

Related papers

• Active Generalized Category Discovery [60.69060965936214]
  Generalized Category Discovery (GCD) endeavors to cluster unlabeled samples from both novel and old classes. We take the spirit of active learning and propose a new setting called Active Generalized Category Discovery (AGCD) Our method achieves state-of-the-art performance on both generic and fine-grained datasets.
  arXiv  Detail & Related papers  (2024-03-07T07:12:24Z)
• Context-Aware Meta-Learning [52.09326317432577]
  We propose a meta-learning algorithm that emulates Large Language Models by learning new visual concepts during inference without fine-tuning. Our approach exceeds or matches the state-of-the-art algorithm, P>M>F, on 8 out of 11 meta-learning benchmarks.
  arXiv  Detail & Related papers  (2023-10-17T03:35:27Z)
• Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation [18.57840057487926]
  Learning from Label Proportions (LLP) is a learning problem where only aggregate level labels are available for groups of instances, called bags, during training. This setting arises in domains like advertising and medicine due to privacy considerations. We propose a novel algorithmic framework for this problem that iteratively performs two main steps.
  arXiv  Detail & Related papers  (2023-10-12T06:09:26Z)
• Improving Zero-Shot Generalization for CLIP with Synthesized Prompts [135.4317555866831]
  Most existing methods require labeled data for all classes, which may not hold in real-world applications. We propose a plug-and-play generative approach called textbfSynttextbfHestextbfIzed textbfPrompts(textbfSHIP) to improve existing fine-tuning methods.
  arXiv  Detail & Related papers  (2023-07-14T15:15:45Z)
• Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels [61.97359362447732]
  Learning from noisy labels is an important and long-standing problem in machine learning for real applications. In this paper, we reformulate the label-noise problem from a generative-model perspective. Our model achieves new state-of-the-art (SOTA) results on all the standard real-world benchmark datasets.
  arXiv  Detail & Related papers  (2023-05-31T03:01:36Z)
• SEAL: Simultaneous Label Hierarchy Exploration And Learning [9.701914280306118]
  We propose a new framework that explores the label hierarchy by augmenting the observed labels with latent labels that follow a prior hierarchical structure. Our approach uses a 1-Wasserstein metric over the tree metric space as an objective function, which enables us to simultaneously learn a data-driven label hierarchy and perform (semi-supervised) learning.
  arXiv  Detail & Related papers  (2023-04-26T08:31:59Z)
• Trustable Co-label Learning from Multiple Noisy Annotators [68.59187658490804]
  Supervised deep learning depends on massive accurately annotated examples. A typical alternative is learning from multiple noisy annotators. This paper proposes a data-efficient approach, called emphTrustable Co-label Learning (TCL)
  arXiv  Detail & Related papers  (2022-03-08T16:57:00Z)
• Learning from Label Proportions by Learning with Label Noise [30.7933303912474]
  Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags. We provide a theoretically grounded approach to LLP based on a reduction to learning with label noise. Our approach demonstrates improved empirical performance in deep learning scenarios across multiple datasets and architectures.
  arXiv  Detail & Related papers  (2022-03-04T18:52:21Z)
• Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification [4.204990010424083]
  We consider a variant of online binary classification where a learner sequentially assigns labels to items with unknown true class. If, but only if, the learner chooses label $1$ they immediately observe the true label of the item. The learner faces a trade-off between short-term classification accuracy and long-term information gain.
  arXiv  Detail & Related papers  (2021-09-29T13:29:01Z)

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.