Balancing Logit Variation for Long-tailed Semantic Segmentation
- URL: http://arxiv.org/abs/2306.02061v1
- Date: Sat, 3 Jun 2023 09:19:24 GMT
- Title: Balancing Logit Variation for Long-tailed Semantic Segmentation
- Authors: Yuchao Wang, Jingjing Fei, Haochen Wang, Wei Li, Tianpeng Bao, Liwei
Wu, Rui Zhao, Yujun Shen
- Abstract summary: We introduce category-wise variation into the network predictions in the training phase.
We close the gap between the feature areas of different categories, resulting in a more balanced representation.
Our method manifests itself in strong generalizability to various datasets and task settings.
- Score: 28.92929059563813
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Semantic segmentation usually suffers from a long-tail data distribution. Due
to the imbalanced number of samples across categories, the features of those
tail classes may get squeezed into a narrow area in the feature space. Towards
a balanced feature distribution, we introduce category-wise variation into the
network predictions in the training phase such that an instance is no longer
projected to a feature point, but a small region instead. Such a perturbation
is highly dependent on the category scale, which appears as assigning smaller
variation to head classes and larger variation to tail classes. In this way, we
manage to close the gap between the feature areas of different categories,
resulting in a more balanced representation. It is noteworthy that the
introduced variation is discarded at the inference stage to facilitate a
confident prediction. Although with an embarrassingly simple implementation,
our method manifests itself in strong generalizability to various datasets and
task settings. Extensive experiments suggest that our plug-in design lends
itself well to a range of state-of-the-art approaches and boosts the
performance on top of them.
Related papers
- Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition [37.62659619941791]
We study the problem of long-tailed visual recognition from the perspective of feature level.
Two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead.
Experiments conducted on benchmark datasets demonstrate the superior performance of the proposed method over the state-of-the-art ones.
arXiv Detail & Related papers (2023-05-18T02:06:06Z) - Constructing Balance from Imbalance for Long-tailed Image Recognition [50.6210415377178]
The imbalance between majority (head) classes and minority (tail) classes severely skews the data-driven deep neural networks.
Previous methods tackle with data imbalance from the viewpoints of data distribution, feature space, and model design.
We propose a concise paradigm by progressively adjusting label space and dividing the head classes and tail classes.
Our proposed model also provides a feature evaluation method and paves the way for long-tailed feature learning.
arXiv Detail & Related papers (2022-08-04T10:22:24Z) - Learning Muti-expert Distribution Calibration for Long-tailed Video
Classification [88.12433458277168]
We propose an end-to-end multi-experts distribution calibration method based on two-level distribution information.
By modeling this two-level distribution information, the model can consider the head classes and the tail classes.
Our method achieves state-of-the-art performance on the long-tailed video classification task.
arXiv Detail & Related papers (2022-05-22T09:52:34Z) - Relieving Long-tailed Instance Segmentation via Pairwise Class Balance [85.53585498649252]
Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes.
It causes severe biases of the head classes (with majority samples) against the tailed ones.
We propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences.
arXiv Detail & Related papers (2022-01-08T07:48:36Z) - 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) - Analyzing Overfitting under Class Imbalance in Neural Networks for Image
Segmentation [19.259574003403998]
In image segmentation neural networks may overfit to the foreground samples from small structures.
In this study, we provide new insights on the problem of overfitting under class imbalance by inspecting the network behavior.
arXiv Detail & Related papers (2021-02-20T14:57:58Z) - Seesaw Loss for Long-Tailed Instance Segmentation [131.86306953253816]
We propose Seesaw Loss to dynamically re-balance gradients of positive and negative samples for each category.
The mitigation factor reduces punishments to tail categories w.r.t. the ratio of cumulative training instances between different categories.
The compensation factor increases the penalty of misclassified instances to avoid false positives of tail categories.
arXiv Detail & Related papers (2020-08-23T12:44:45Z) - 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) - Deep Representation Learning on Long-tailed Data: A Learnable Embedding
Augmentation Perspective [17.602607883721973]
In the deep feature space, the head classes and the tail classes present different distribution patterns.
We propose to construct each feature into a "feature cloud"
It allows each tail sample to push the samples from other classes far away, recovering the intra-class diversity of tail classes.
arXiv Detail & Related papers (2020-02-25T12:38:32Z)
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.