Feature Space Augmentation for Long-Tailed Data

• URL: http://arxiv.org/abs/2008.03673v1
• Date: Sun, 9 Aug 2020 06:38:00 GMT
• Title: Feature Space Augmentation for Long-Tailed Data
• Authors: Peng Chu and Xiao Bian and Shaopeng Liu and Haibin Ling
• Abstract summary: Real-world data often follow a long-tailed distribution as the frequency of each class is typically different. Class-balanced loss and advanced methods on data re-sampling and augmentation are among the best practices to alleviate the data imbalance problem. We present a novel approach to address the long-tailed problem by augmenting the under-represented classes in the feature space with the features learned from the classes with ample samples.
• Score: 74.65615132238291
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world data often follow a long-tailed distribution as the frequency of each class is typically different. For example, a dataset can have a large number of under-represented classes and a few classes with more than sufficient data. However, a model to represent the dataset is usually expected to have reasonably homogeneous performances across classes. Introducing class-balanced loss and advanced methods on data re-sampling and augmentation are among the best practices to alleviate the data imbalance problem. However, the other part of the problem about the under-represented classes will have to rely on additional knowledge to recover the missing information. In this work, we present a novel approach to address the long-tailed problem by augmenting the under-represented classes in the feature space with the features learned from the classes with ample samples. In particular, we decompose the features of each class into a class-generic component and a class-specific component using class activation maps. Novel samples of under-represented classes are then generated on the fly during training stages by fusing the class-specific features from the under-represented classes with the class-generic features from confusing classes. Our results on different datasets such as iNaturalist, ImageNet-LT, Places-LT and a long-tailed version of CIFAR have shown the state of the art performances.

Related papers

• 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)
• Instance-level Few-shot Learning with Class Hierarchy Mining [26.273796311012042]
  We exploit hierarchical information to leverage discriminative and relevant features of base classes to effectively classify novel objects. These features are extracted from abundant data of base classes, which could be utilized to reasonably describe classes with scarce data. In order to effectively train the hierarchy-based-detector in FSIS, we apply the label refinement to further describe the associations between fine-grained classes.
  arXiv  Detail & Related papers  (2023-04-15T02:55:08Z)
• Unicom: Universal and Compact Representation Learning for Image Retrieval [65.96296089560421]
  We cluster the large-scale LAION400M into one million pseudo classes based on the joint textual and visual features extracted by the CLIP model. To alleviate such conflict, we randomly select partial inter-class prototypes to construct the margin-based softmax loss. Our method significantly outperforms state-of-the-art unsupervised and supervised image retrieval approaches on multiple benchmarks.
  arXiv  Detail & Related papers  (2023-04-12T14:25:52Z)
• 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)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• AlphaNet: Improving Long-Tail Classification By Combining Classifiers [44.5124310374697]
  Methods in long-tail learning focus on improving performance for data-poor (rare) classes. A large number of errors are due to misclassification of rare items as visually similar frequent classes. We introduce AlphaNet, a method that can be applied to existing models, performing post hoc correction on classifiers of rare classes.
  arXiv  Detail & Related papers  (2020-08-17T03:31:39Z)
• A Few-Shot Sequential Approach for Object Counting [63.82757025821265]
  We introduce a class attention mechanism that sequentially attends to objects in the image and extracts their relevant features. The proposed technique is trained on point-level annotations and uses a novel loss function that disentangles class-dependent and class-agnostic aspects of the model. We present our results on a variety of object-counting/detection datasets, including FSOD and MS COCO.
  arXiv  Detail & Related papers  (2020-07-03T18:23:39Z)
• Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective [98.70226503904402]
  Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions. We propose to augment the classic class-balanced learning by explicitly estimating the differences between the class-conditioned distributions with a meta-learning approach.
  arXiv  Detail & Related papers  (2020-03-24T11:28:42Z)

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.