Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory

• URL: http://arxiv.org/abs/2008.09809v6
• Date: Tue, 6 Jul 2021 07:49:04 GMT
• Title: Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory
• Authors: Jialun Liu, Jingwei Zhang, Yi yang, Wenhui Li, Chi Zhang and Yifan Sun
• Abstract summary: We introduce a simple and reliable method named Memory-based Jitter (MBJ) to augment the tail classes with higher diversity. MBJ is applicable for two fundamental visual recognition tasks, emphi.e., deep image classification and deep metric learning. Experiments on five long-tailed classification benchmarks and two deep metric learning benchmarks demonstrate significant improvement.
• Score: 39.56214005885884
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper considers deep visual recognition on long-tailed data. To be general, we consider two applied scenarios, \ie, deep classification and deep metric learning. Under the long-tailed data distribution, the majority classes (\ie, tail classes) only occupy relatively few samples and are prone to lack of within-class diversity. A radical solution is to augment the tail classes with higher diversity. To this end, we introduce a simple and reliable method named Memory-based Jitter (MBJ). We observe that during training, the deep model constantly changes its parameters after every iteration, yielding the phenomenon of \emph{weight jitters}. Consequentially, given a same image as the input, two historical editions of the model generate two different features in the deeply-embedded space, resulting in \emph{feature jitters}. Using a memory bank, we collect these (model or feature) jitters across multiple training iterations and get the so-called Memory-based Jitter. The accumulated jitters enhance the within-class diversity for the tail classes and consequentially improves long-tailed visual recognition. With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, \emph{i.e.}, deep image classification and deep metric learning (on long-tailed data). Extensive experiments on five long-tailed classification benchmarks and two deep metric learning benchmarks demonstrate significant improvement. Moreover, the achieved performance are on par with the state of the art on both tasks.

Related papers

• Holistic Memory Diversification for Incremental Learning in Growing Graphs [16.483780704430405]
  The goal is to continually train a graph model to handle new tasks while retaining its inference ability on previous tasks. Existing methods usually neglect the importance of memory diversity, limiting in effectively selecting high-quality memory from previous tasks. We introduce a novel holistic Diversified Memory Selection and Generation framework for incremental learning in graphs.
  arXiv  Detail & Related papers  (2024-06-11T16:18:15Z)
• Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memory [59.51934126717572]
  Black-box unsupervised domain adaptation (UDA) learns with source predictions of target data without accessing either source data or source models during training. We propose BiMem, a bi-directional memorization mechanism that learns to remember useful and representative information to correct noisy pseudo labels on the fly. BiMem achieves superior domain adaptation performance consistently across various visual recognition tasks such as image classification, semantic segmentation and object detection.
  arXiv  Detail & Related papers  (2023-08-25T08:06:48Z)
• Improving Image Recognition by Retrieving from Web-Scale Image-Text Data [68.63453336523318]
  We introduce an attention-based memory module, which learns the importance of each retrieved example from the memory. Compared to existing approaches, our method removes the influence of the irrelevant retrieved examples, and retains those that are beneficial to the input query. We show that it achieves state-of-the-art accuracies in ImageNet-LT, Places-LT and Webvision datasets.
  arXiv  Detail & Related papers  (2023-04-11T12:12:05Z)
• A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning [56.450090618578]
  Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. We show that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work. We propose a simple yet effective baseline, denoted as MEMO for Memory-efficient Expandable MOdel.
  arXiv  Detail & Related papers  (2022-05-26T08:24:01Z)
• Memory-Guided Semantic Learning Network for Temporal Sentence Grounding [55.31041933103645]
  We propose a memory-augmented network that learns and memorizes the rarely appeared content in TSG tasks. MGSL-Net consists of three main parts: a cross-modal inter-action module, a memory augmentation module, and a heterogeneous attention module.
  arXiv  Detail & Related papers  (2022-01-03T02:32:06Z)
• Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models [9.848884631714451]
  Memory Wrap is a plug-and-play extension to any image classification model. It improves both data-efficiency and model interpretability, adopting a content-attention mechanism. We show that Memory Wrap outperforms standard classifiers when it learns from a limited set of data.
  arXiv  Detail & Related papers  (2021-06-01T07:24:19Z)
• 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)

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.