Memory Efficient Class-Incremental Learning for Image Classification
- URL: http://arxiv.org/abs/2008.01411v2
- Date: Tue, 18 May 2021 13:32:08 GMT
- Title: Memory Efficient Class-Incremental Learning for Image Classification
- Authors: Hanbin Zhao, Hui Wang, Yongjian Fu, Fei Wu, Xi Li
- Abstract summary: Class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes.
We propose to keep more auxiliary low-fidelity exemplar samples rather than the original real high-fidelity exemplar samples.
- Score: 23.666101443616995
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: With the memory-resource-limited constraints, class-incremental learning
(CIL) usually suffers from the "catastrophic forgetting" problem when updating
the joint classification model on the arrival of newly added classes. To cope
with the forgetting problem, many CIL methods transfer the knowledge of old
classes by preserving some exemplar samples into the size-constrained memory
buffer. To utilize the memory buffer more efficiently, we propose to keep more
auxiliary low-fidelity exemplar samples rather than the original real
high-fidelity exemplar samples. Such a memory-efficient exemplar preserving
scheme makes the old-class knowledge transfer more effective. However, the
low-fidelity exemplar samples are often distributed in a different domain away
from that of the original exemplar samples, that is, a domain shift. To
alleviate this problem, we propose a duplet learning scheme that seeks to
construct domain-compatible feature extractors and classifiers, which greatly
narrows down the above domain gap. As a result, these low-fidelity auxiliary
exemplar samples have the ability to moderately replace the original exemplar
samples with a lower memory cost. In addition, we present a robust classifier
adaptation scheme, which further refines the biased classifier (learned with
the samples containing distillation label knowledge about old classes) with the
help of the samples of pure true class labels. Experimental results demonstrate
the effectiveness of this work against the state-of-the-art approaches.
Related papers
- Efficient Non-Exemplar Class-Incremental Learning with Retrospective Feature Synthesis [21.348252135252412]
Current Non-Exemplar Class-Incremental Learning (NECIL) methods mitigate forgetting by storing a single prototype per class.
We propose a more efficient NECIL method that replaces prototypes with synthesized retrospective features for old classes.
Our method significantly improves the efficiency of non-exemplar class-incremental learning and achieves state-of-the-art performance.
arXiv Detail & Related papers (2024-11-03T07:19:11Z) - Adaptive Intra-Class Variation Contrastive Learning for Unsupervised Person Re-Identification [10.180143197144803]
We propose an adaptive intra-class variation contrastive learning algorithm for unsupervised Re-ID, called AdaInCV.
The algorithm quantitatively evaluates the learning ability of the model for each class by considering the intra-class variations after clustering.
To be more specific, two new strategies are proposed: Adaptive Sample Mining (AdaSaM) and Adaptive Outlier Filter (AdaOF)
arXiv Detail & Related papers (2024-04-06T15:48:14Z) - Class incremental learning with probability dampening and cascaded gated classifier [4.285597067389559]
We propose a novel incremental regularisation approach called Margin Dampening and Cascaded Scaling.
The first combines a soft constraint and a knowledge distillation approach to preserve past knowledge while allowing forgetting new patterns.
We empirically show that our approach performs well on multiple benchmarks well-established baselines.
arXiv Detail & Related papers (2024-02-02T09:33:07Z) - Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning [59.44422468242455]
We propose a novel method dubbed ShrinkMatch to learn uncertain samples.
For each uncertain sample, it adaptively seeks a shrunk class space, which merely contains the original top-1 class.
We then impose a consistency regularization between a pair of strongly and weakly augmented samples in the shrunk space to strive for discriminative representations.
arXiv Detail & Related papers (2023-08-13T14:05:24Z) - Generalization Bounds for Few-Shot Transfer Learning with Pretrained
Classifiers [26.844410679685424]
We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes.
We show that the few-shot error of the learned feature map on new classes is small in case of class-feature-variability collapse.
arXiv Detail & Related papers (2022-12-23T18:46:05Z) - Intra-class Adaptive Augmentation with Neighbor Correction for Deep
Metric Learning [99.14132861655223]
We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning.
We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining.
Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
arXiv Detail & Related papers (2022-11-29T14:52:38Z) - 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) - Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated
Label Mixing [104.630875328668]
Mixup scheme suggests mixing a pair of samples to create an augmented training sample.
We present a novel, yet simple Mixup-variant that captures the best of both worlds.
arXiv Detail & Related papers (2021-12-16T11:27:48Z) - Latent-Insensitive Autoencoders for Anomaly Detection and
Class-Incremental Learning [0.0]
We introduce Latent-Insensitive Autoencoder (LIS-AE) where unlabeled data from a similar domain is utilized as negative examples to shape the latent layer (bottleneck) of a regular autoencoder.
We treat class-incremental learning as multiple anomaly detection tasks by adding a different latent layer for each class and use other available classes in task as negative examples to shape each latent layer.
arXiv Detail & Related papers (2021-10-25T16:53:49Z) - Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed
Recognition [95.93760490301395]
The problem of long-tailed recognition, where the number of examples per class is highly unbalanced, is considered.
It is hypothesized that this is due to the repeated sampling of examples and can be addressed by feature space augmentation.
A new feature augmentation strategy, EMANATE, based on back-tracking of features across epochs during training, is proposed.
A new sampling procedure, Breadcrumb, is then introduced to implement adversarial class-balanced sampling without extra computation.
arXiv Detail & Related papers (2021-05-01T00:21:26Z) - Improving memory banks for unsupervised learning with large mini-batch,
consistency and hard negative mining [61.223064077782645]
We introduce 3 improvements to the vanilla memory bank-based formulation which brings massive accuracy gains.
We enforce the logits obtained by different augmentations of the same sample to be close without trying to enforce discrimination with respect to negative samples.
Since instance discrimination is not meaningful for samples that are too visually similar, we devise a novel nearest neighbour approach for improving the memory bank.
arXiv Detail & Related papers (2021-02-08T18:56:33Z)
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.