Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class

• URL: http://arxiv.org/abs/2404.16717v1
• Date: Thu, 25 Apr 2024 16:29:06 GMT
• Title: Embracing Diversity: Interpretable Zero-shot classification beyond one vector per class
• Authors: Mazda Moayeri, Michael Rabbat, Mark Ibrahim, Diane Bouchacourt,
• Abstract summary: We argue that to represent diversity within a class, zero-shot classification should move beyond a single vector. We propose a method to encode and account for diversity within a class using inferred attributes, still in the zero-shot setting without retraining. We find our method consistently outperforms standard zero-shot classification over a large suite of datasets.
• Score: 16.101460010750458
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models enable open-world classification of objects without the need for any retraining. While this zero-shot paradigm marks a significant advance, even today's best models exhibit skewed performance when objects are dissimilar from their typical depiction. Real world objects such as pears appear in a variety of forms -- from diced to whole, on a table or in a bowl -- yet standard VLM classifiers map all instances of a class to a \it{single vector based on the class label}. We argue that to represent this rich diversity within a class, zero-shot classification should move beyond a single vector. We propose a method to encode and account for diversity within a class using inferred attributes, still in the zero-shot setting without retraining. We find our method consistently outperforms standard zero-shot classification over a large suite of datasets encompassing hierarchies, diverse object states, and real-world geographic diversity, as well finer-grained datasets where intra-class diversity may be less prevalent. Importantly, our method is inherently interpretable, offering faithful explanations for each inference to facilitate model debugging and enhance transparency. We also find our method scales efficiently to a large number of attributes to account for diversity -- leading to more accurate predictions for atypical instances. Finally, we characterize a principled trade-off between overall and worst class accuracy, which can be tuned via a hyperparameter of our method. We hope this work spurs further research into the promise of zero-shot classification beyond a single class vector for capturing diversity in the world, and building transparent AI systems without compromising performance.

Related papers

• Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks [10.556477506959888]
  Existing methods often encounter difficulties in drawing accurate class prototypes from support set samples. Recent approaches attempt to incorporate external knowledge or pre-trained language models to augment data, but this requires additional resources. We propose a novel solution by adequately leveraging the information within the task itself.
  arXiv  Detail & Related papers  (2024-10-14T12:47:11Z)
• LLM meets Vision-Language Models for Zero-Shot One-Class Classification [4.094697851983375]
  We consider the problem of zero-shot one-class visual classification. We propose a two-step solution that first queries large language models for visually confusing objects. We are the first to demonstrate the ability to discriminate a single category from other semantically related ones using only its label.
  arXiv  Detail & Related papers  (2024-03-31T12:48:07Z)
• Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment [53.2701026843921]
  Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
  arXiv  Detail & Related papers  (2023-08-24T17:56:46Z)
• Unicom: Universal and Compact Representation Learning for Image Retrieval [65.96296089560421]
  We cluster the large-scale LAION400M into one million pseudo classes based on the joint textual and visual features extracted by the CLIP model. To alleviate such conflict, we randomly select partial inter-class prototypes to construct the margin-based softmax loss. Our method significantly outperforms state-of-the-art unsupervised and supervised image retrieval approaches on multiple benchmarks.
  arXiv  Detail & Related papers  (2023-04-12T14:25:52Z)
• Multi-Class Classification from Single-Class Data with Confidences [90.48669386745361]
  We propose an empirical risk minimization framework that is loss-/model-/optimizer-independent. We show that our method can be Bayes-consistent with a simple modification even if the provided confidences are highly noisy.
  arXiv  Detail & Related papers  (2021-06-16T15:38:13Z)
• 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)
• Learning and Evaluating Representations for Deep One-class Classification [59.095144932794646]
  We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T23:33:41Z)
• Meta Learning for Few-Shot One-class Classification [0.0]
  We formulate the learning of meaningful features for one-class classification as a meta-learning problem. To learn these representations, we require only multiclass data from similar tasks. We validate our approach by adapting few-shot classification datasets to the few-shot one-class classification scenario.
  arXiv  Detail & Related papers  (2020-09-11T11:35:28Z)
• Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification [91.67977602992657]
  We propose a new strategy based on feature selection, which is both simpler and more effective than previous feature adaptation approaches. We show that a simple non-parametric classifier built on top of such features produces high accuracy and generalizes to domains never seen during training.
  arXiv  Detail & Related papers  (2020-03-20T15:44:17Z)
• Weakly-supervised Object Localization for Few-shot Learning and Fine-grained Few-shot Learning [0.5156484100374058]
  Few-shot learning aims to learn novel visual categories from very few samples. We propose a Self-Attention Based Complementary Module (SAC Module) to fulfill the weakly-supervised object localization. We also produce the activated masks for selecting discriminative deep descriptors for few-shot classification.
  arXiv  Detail & Related papers  (2020-03-02T14:07:05Z)

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.