Learning Towards the Largest Margins
- URL: http://arxiv.org/abs/2206.11589v1
- Date: Thu, 23 Jun 2022 10:03:03 GMT
- Title: Learning Towards the Largest Margins
- Authors: Xiong Zhou, Xianming Liu, Deming Zhai, Junjun Jiang, Xin Gao,
Xiangyang Ji
- Abstract summary: Loss function should promote the largest possible margins for both classes and samples.
Not only does this principled framework offer new perspectives to understand and interpret existing margin-based losses, but it can guide the design of new tools.
- Score: 83.7763875464011
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: One of the main challenges for feature representation in deep learning-based
classification is the design of appropriate loss functions that exhibit strong
discriminative power. The classical softmax loss does not explicitly encourage
discriminative learning of features. A popular direction of research is to
incorporate margins in well-established losses in order to enforce extra
intra-class compactness and inter-class separability, which, however, were
developed through heuristic means, as opposed to rigorous mathematical
principles. In this work, we attempt to address this limitation by formulating
the principled optimization objective as learning towards the largest margins.
Specifically, we firstly define the class margin as the measure of inter-class
separability, and the sample margin as the measure of intra-class compactness.
Accordingly, to encourage discriminative representation of features, the loss
function should promote the largest possible margins for both classes and
samples. Furthermore, we derive a generalized margin softmax loss to draw
general conclusions for the existing margin-based losses. Not only does this
principled framework offer new perspectives to understand and interpret
existing margin-based losses, but it also provides new insights that can guide
the design of new tools, including sample margin regularization and largest
margin softmax loss for the class-balanced case, and zero-centroid
regularization for the class-imbalanced case. Experimental results demonstrate
the effectiveness of our strategy on a variety of tasks, including visual
classification, imbalanced classification, person re-identification, and face
verification.
Related papers
- Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric [99.19559537966538]
DML aims to learn a discriminative high-dimensional embedding space for downstream tasks like classification, clustering, and retrieval.
To maintain the structure of embedding space and avoid feature collapse, we propose a novel loss function called Anti-Collapse Loss.
Comprehensive experiments on benchmark datasets demonstrate that our proposed method outperforms existing state-of-the-art methods.
arXiv Detail & Related papers (2024-07-03T13:44:20Z) - A Universal Class of Sharpness-Aware Minimization Algorithms [57.29207151446387]
We introduce a new class of sharpness measures, leading to new sharpness-aware objective functions.
We prove that these measures are textitly expressive, allowing any function of the training loss Hessian matrix to be represented by appropriate hyper and determinants.
arXiv Detail & Related papers (2024-06-06T01:52:09Z) - Large Margin Discriminative Loss for Classification [3.3975558777609915]
We introduce a novel discriminative loss function with large margin in the context of Deep Learning.
This loss boosts the discriminative power of neural nets, represented by intra-class compactness and inter-class separability.
arXiv Detail & Related papers (2024-05-28T18:10:45Z) - Unified Binary and Multiclass Margin-Based Classification [27.28814893730265]
We show that a broad range of multiclass loss functions, including many popular ones, can be expressed in the relative margin form.
We then analyze the class of Fenchel-Young losses, and expand the set of these losses that are known to be classification-calibrated.
arXiv Detail & Related papers (2023-11-29T16:24:32Z) - Joint Discriminative and Metric Embedding Learning for Person
Re-Identification [8.137833258504381]
Person re-identification is a challenging task because of the high intra-class variance induced by the unrestricted nuisance factors of variations.
Recent approaches postulate that powerful architectures have the capacity to learn feature representations invariant to nuisance factors.
arXiv Detail & Related papers (2022-12-28T22:08:42Z) - Learning Imbalanced Datasets with Maximum Margin Loss [21.305656747991026]
A learning algorithm referred to as Maximum Margin (MM) is proposed for considering the class-imbalance data learning issue.
We design a new Maximum Margin (MM) loss function, motivated by minimizing a margin-based generalization bound through the shifting decision bound.
arXiv Detail & Related papers (2022-06-11T00:21:41Z) - Distribution of Classification Margins: Are All Data Equal? [61.16681488656473]
We motivate theoretically and show empirically that the area under the curve of the margin distribution on the training set is in fact a good measure of generalization.
The resulting subset of "high capacity" features is not consistent across different training runs.
arXiv Detail & Related papers (2021-07-21T16:41:57Z) - Boosting Few-Shot Learning With Adaptive Margin Loss [109.03665126222619]
This paper proposes an adaptive margin principle to improve the generalization ability of metric-based meta-learning approaches for few-shot learning problems.
Extensive experiments demonstrate that the proposed method can boost the performance of current metric-based meta-learning approaches.
arXiv Detail & Related papers (2020-05-28T07:58:41Z) - Negative Margin Matters: Understanding Margin in Few-shot Classification [72.85978953262004]
This paper introduces a negative margin loss to metric learning based few-shot learning methods.
The negative margin loss significantly outperforms regular softmax loss, and state-of-the-art accuracy on three standard few-shot classification benchmarks.
arXiv Detail & Related papers (2020-03-26T17:59:05Z)
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.