Invariant Feature Learning for Generalized Long-Tailed Classification
- URL: http://arxiv.org/abs/2207.09504v2
- Date: Sat, 1 Apr 2023 12:11:14 GMT
- Title: Invariant Feature Learning for Generalized Long-Tailed Classification
- Authors: Kaihua Tang, Mingyuan Tao, Jiaxin Qi, Zhenguang Liu, Hanwang Zhang
- Abstract summary: We introduce Generalized Long-Tailed classification (GLT) to jointly consider both kinds of imbalances.
We argue that most class-wise LT methods degenerate in our proposed two benchmarks: ImageNet-GLT and MSCOCO-GLT.
We propose an Invariant Feature Learning (IFL) method as the first strong baseline for GLT.
- Score: 63.0533733524078
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing long-tailed classification (LT) methods only focus on tackling the
class-wise imbalance that head classes have more samples than tail classes, but
overlook the attribute-wise imbalance. In fact, even if the class is balanced,
samples within each class may still be long-tailed due to the varying
attributes. Note that the latter is fundamentally more ubiquitous and
challenging than the former because attributes are not just implicit for most
datasets, but also combinatorially complex, thus prohibitively expensive to be
balanced. Therefore, we introduce a novel research problem: Generalized
Long-Tailed classification (GLT), to jointly consider both kinds of imbalances.
By "generalized", we mean that a GLT method should naturally solve the
traditional LT, but not vice versa. Not surprisingly, we find that most
class-wise LT methods degenerate in our proposed two benchmarks: ImageNet-GLT
and MSCOCO-GLT. We argue that it is because they over-emphasize the adjustment
of class distribution while neglecting to learn attribute-invariant features.
To this end, we propose an Invariant Feature Learning (IFL) method as the first
strong baseline for GLT. IFL first discovers environments with divergent
intra-class distributions from the imperfect predictions and then learns
invariant features across them. Promisingly, as an improved feature backbone,
IFL boosts all the LT line-up: one/two-stage re-balance, augmentation, and
ensemble. Codes and benchmarks are available on Github:
https://github.com/KaihuaTang/Generalized-Long-Tailed-Benchmarks.pytorch
Related papers
- Boosting Consistency in Dual Training for Long-Tailed Semi-Supervised Learning [49.07038093130949]
Long-tailed semi-supervised learning (LTSSL) algorithms assume that the class distributions of labeled and unlabeled data are almost identical.
We propose a new simple method that can effectively utilize unlabeled data from unknown class distributions.
We show that BOAT achieves state-of-the-art performance on a variety of standard LTSSL benchmarks.
arXiv Detail & Related papers (2024-06-19T03:35:26Z) - Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning [74.44500692632778]
We propose a novel method named ComPlementary Experts (CPE) to model various class distributions.
CPE achieves state-of-the-art performances on CIFAR-10-LT, CIFAR-100-LT, and STL-10-LT dataset benchmarks.
arXiv Detail & Related papers (2023-12-25T11:54:07Z) - Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss [20.10399273585125]
Long-tailed (LT) classification is an unavoidable and challenging problem in the real world.
We propose a novel long-tailed classification framework, aiming to build a multi-granularity classification model by means of invariant feature learning.
Our approach achieves state-of-the-art performance on both existing benchmarks ImageNet-GLT and MSCOCO-GLT.
arXiv Detail & Related papers (2023-10-12T10:51:23Z) - Subclass-balancing Contrastive Learning for Long-tailed Recognition [38.31221755013738]
Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications.
We propose a novel subclass-balancing contrastive learning'' approach that clusters each head class into multiple subclasses of similar sizes as the tail classes.
We evaluate SBCL over a list of long-tailed benchmark datasets and it achieves the state-of-the-art performance.
arXiv Detail & Related papers (2023-06-28T05:08:43Z) - Long-Tailed Class Incremental Learning [72.4894111493918]
In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones.
We propose two long-tailed CIL scenarios, which we term ordered and shuffled LT-CIL.
Our results demonstrate the superior performance (up to 6.44 points in average incremental accuracy) of our approach on CIFAR-100 and ImageNet-Subset.
arXiv Detail & Related papers (2022-10-01T12:41:48Z) - Balanced Contrastive Learning for Long-Tailed Visual Recognition [32.789465918318925]
Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data.
In this paper, we focus on representation learning for imbalanced data.
We propose a novel loss for balanced contrastive learning (BCL)
arXiv Detail & Related papers (2022-07-19T03:48:59Z) - Do Deep Networks Transfer Invariances Across Classes? [123.84237389985236]
We show how a generative approach for learning the nuisance transformations can help transfer invariances across classes.
Our results provide one explanation for why classifiers generalize poorly on unbalanced and longtailed distributions.
arXiv Detail & Related papers (2022-03-18T04:38:18Z) - 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.