Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models

• URL: http://arxiv.org/abs/2106.01440v1
• Date: Tue, 1 Jun 2021 07:24:19 GMT
• Title: Memory Wrap: a Data-Efficient and Interpretable Extension to Image Classification Models
• Authors: Biagio La Rosa, Roberto Capobianco and Daniele Nardi
• Abstract summary: 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.
• Score: 9.848884631714451
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to their black-box and data-hungry nature, deep learning techniques are not yet widely adopted for real-world applications in critical domains, like healthcare and justice. This paper presents Memory Wrap, a plug-and-play extension to any image classification model. Memory Wrap improves both data-efficiency and model interpretability, adopting a content-attention mechanism between the input and some memories of past training samples. We show that Memory Wrap outperforms standard classifiers when it learns from a limited set of data, and it reaches comparable performance when it learns from the full dataset. We discuss how its structure and content-attention mechanisms make predictions interpretable, compared to standard classifiers. To this end, we both show a method to build explanations by examples and counterfactuals, based on the memory content, and how to exploit them to get insights about its decision process. We test our approach on image classification tasks using several architectures on three different datasets, namely CIFAR10, SVHN, and CINIC10.

Related papers

• 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)
• Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform [3.630365560970225]
  Recent methods with learning gradient have been shown to struggle in such setups or have limitations like memory buffers. We present a fully differentiable architecture based on the Mixture of Experts model, that enables the training of high-performance classifiers when examples from each class are presented separately. We conducted exhaustive experiments that proved its applicability in various domains and ability to learn online in production environments.
  arXiv  Detail & Related papers  (2023-07-11T16:01:44Z)
• 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 Memory Transformer Network for Incremental Learning [64.0410375349852]
  We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to class-incremental learning results in the "catastrophic forgetting" of previously seen classes. One of the most successful existing methods has been the use of a memory of exemplars, which overcomes the issue of catastrophic forgetting by saving a subset of past data into a memory bank and utilizing it to prevent forgetting when training future tasks.
  arXiv  Detail & Related papers  (2022-10-10T08:27:28Z)
• Memory Classifiers: Two-stage Classification for Robustness in Machine Learning [19.450529711560964]
  We propose a new method for classification which can improve robustness to distribution shifts. We combine expert knowledge about the high-level" structure of the data with standard classifiers. We show improvements which push beyond standard data augmentation techniques.
  arXiv  Detail & Related papers  (2022-06-10T18:44:45Z)
• 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)
• Hierarchical Variational Memory for Few-shot Learning Across Domains [120.87679627651153]
  We introduce a hierarchical prototype model, where each level of the prototype fetches corresponding information from the hierarchical memory. The model is endowed with the ability to flexibly rely on features at different semantic levels if the domain shift circumstances so demand. We conduct thorough ablation studies to demonstrate the effectiveness of each component in our model.
  arXiv  Detail & Related papers  (2021-12-15T15:01:29Z)
• Multi-dataset Pretraining: A Unified Model for Semantic Segmentation [97.61605021985062]
  We propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented annotations of different datasets. This is achieved by first pretraining the network via the proposed pixel-to-prototype contrastive loss over multiple datasets. In order to better model the relationship among images and classes from different datasets, we extend the pixel level embeddings via cross dataset mixing.
  arXiv  Detail & Related papers  (2021-06-08T06:13:11Z)
• Rainbow Memory: Continual Learning with a Memory of Diverse Samples [14.520337285540148]
  We argue the importance of diversity of samples in an episodic memory. We propose a novel memory management strategy based on per-sample classification uncertainty and data augmentation. We show that the proposed method significantly improves the accuracy in blurry continual learning setups.
  arXiv  Detail & Related papers  (2021-03-31T17:28:29Z)
• Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory [39.56214005885884]
  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.
  arXiv  Detail & Related papers  (2020-08-22T11:01:46Z)

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.