Test-Agnostic Long-Tailed Recognition by Test-Time Aggregating Diverse Experts with Self-Supervision

• URL: http://arxiv.org/abs/2107.09249v1
• Date: Tue, 20 Jul 2021 04:10:31 GMT
• Title: Test-Agnostic Long-Tailed Recognition by Test-Time Aggregating Diverse Experts with Self-Supervision
• Authors: Yifan Zhang, Bryan Hooi, Lanqing Hong, Jiashi Feng
• Abstract summary: We study a more practical task setting, called test-agnostic long-tailed recognition, where the training class distribution is long-tailed. We propose a new method, called Test-time Aggregating Diverse Experts (TADE), that trains diverse experts to excel at handling different test distributions. We theoretically show that our method has provable ability to simulate unknown test class distributions.
• Score: 85.07855130048951
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing long-tailed recognition methods, aiming to train class-balance models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution. However, the practical test class distribution often violates such an assumption (e.g., being long-tailed or even inversely long-tailed), which would lead existing methods to fail in real-world applications. In this work, we study a more practical task setting, called test-agnostic long-tailed recognition, where the training class distribution is long-tailed while the test class distribution is unknown and can be skewed arbitrarily. In addition to the issue of class imbalance, this task poses another challenge: the class distribution shift between the training and test samples is unidentified. To address this task, we propose a new method, called Test-time Aggregating Diverse Experts (TADE), that presents two solution strategies: (1) a novel skill-diverse expert learning strategy that trains diverse experts to excel at handling different test distributions from a single long-tailed training distribution; (2) a novel test-time expert aggregation strategy that leverages self-supervision to aggregate multiple experts for handling various test distributions. Moreover, we theoretically show that our method has provable ability to simulate unknown test class distributions. Promising results on both vanilla and test-agnostic long-tailed recognition verify the effectiveness of TADE. Code is available at https://github.com/Vanint/TADE-AgnosticLT.

Related papers

• DOTA: Distributional Test-Time Adaptation of Vision-Language Models [52.98590762456236]
  Training-free test-time dynamic adapter (TDA) is a promising approach to address this issue. We propose a simple yet effective method for DistributiOnal Test-time Adaptation (Dota) Dota continually estimates the distributions of test samples, allowing the model to continually adapt to the deployment environment.
  arXiv  Detail & Related papers  (2024-09-28T15:03:28Z)
• Any-Shift Prompting for Generalization over Distributions [66.29237565901734]
  We propose any-shift prompting: a general probabilistic inference framework that considers the relationship between training and test distributions during prompt learning. Within this framework, the test prompt exploits the distribution relationships to guide the generalization of the CLIP image-language model from training to any test distribution. The network generates the tailored test prompt with both training and test information in a feedforward pass, avoiding extra training costs at test time.
  arXiv  Detail & Related papers  (2024-02-15T16:53:42Z)
• ClusT3: Information Invariant Test-Time Training [19.461441044484427]
  Test-time training (TTT) methods have been developed in an attempt to mitigate these vulnerabilities. We propose a novel unsupervised TTT technique based on the Mutual of Mutual Information between multi-scale feature maps and a discrete latent representation. Experimental results demonstrate competitive classification performance on different popular test-time adaptation benchmarks.
  arXiv  Detail & Related papers  (2023-10-18T21:43:37Z)
• Test-Time Adaptation with Perturbation Consistency Learning [32.58879780726279]
  We propose a simple test-time adaptation method to promote the model to make stable predictions for samples with distribution shifts. Our method can achieve higher or comparable performance with less inference time over strong PLM backbones.
  arXiv  Detail & Related papers  (2023-04-25T12:29:22Z)
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts [143.14128737978342]
  Test-time adaptation, an emerging paradigm, has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions. Recent progress in this paradigm highlights the significant benefits of utilizing unlabeled data for training self-adapted models prior to inference.
  arXiv  Detail & Related papers  (2023-03-27T16:32:21Z)
• Revisiting Long-tailed Image Classification: Survey and Benchmarks with New Evaluation Metrics [88.39382177059747]
  A corpus of metrics is designed for measuring the accuracy, robustness, and bounds of algorithms for learning with long-tailed distribution. Based on our benchmarks, we re-evaluate the performance of existing methods on CIFAR10 and CIFAR100 datasets.
  arXiv  Detail & Related papers  (2023-02-03T02:40:54Z)
• Balanced Product of Calibrated Experts for Long-Tailed Recognition [13.194151879344487]
  Many real-world recognition problems are characterized by long-tailed label distributions. In this work, we take an analytical approach and extend the notion of logit adjustment to ensembles to form a Balanced Product of Experts (BalPoE) We show how to properly define these distributions and combine the experts in order to achieve unbiased predictions.
  arXiv  Detail & Related papers  (2022-06-10T17:59:02Z)
• Understanding Classifier Mistakes with Generative Models [88.20470690631372]
  Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle. In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
  arXiv  Detail & Related papers  (2020-10-05T22:13:21Z)

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.