SuperDisco: Super-Class Discovery Improves Visual Recognition for the
Long-Tail
- URL: http://arxiv.org/abs/2304.00101v1
- Date: Fri, 31 Mar 2023 19:51:12 GMT
- Title: SuperDisco: Super-Class Discovery Improves Visual Recognition for the
Long-Tail
- Authors: Yingjun Du, Jiayi Shen, Xiantong Zhen, Cees G. M. Snoek
- Abstract summary: We propose SuperDisco, an algorithm that discovers super-class representations for long-tailed recognition.
We learn to construct the super-class graph to guide the representation learning to deal with long-tailed distributions.
- Score: 69.50380510879697
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Modern image classifiers perform well on populated classes, while degrading
considerably on tail classes with only a few instances. Humans, by contrast,
effortlessly handle the long-tailed recognition challenge, since they can learn
the tail representation based on different levels of semantic abstraction,
making the learned tail features more discriminative. This phenomenon motivated
us to propose SuperDisco, an algorithm that discovers super-class
representations for long-tailed recognition using a graph model. We learn to
construct the super-class graph to guide the representation learning to deal
with long-tailed distributions. Through message passing on the super-class
graph, image representations are rectified and refined by attending to the most
relevant entities based on the semantic similarity among their super-classes.
Moreover, we propose to meta-learn the super-class graph under the supervision
of a prototype graph constructed from a small amount of imbalanced data. By
doing so, we obtain a more robust super-class graph that further improves the
long-tailed recognition performance. The consistent state-of-the-art
experiments on the long-tailed CIFAR-100, ImageNet, Places and iNaturalist
demonstrate the benefit of the discovered super-class graph for dealing with
long-tailed distributions.
Related papers
- Disentangled Generative Graph Representation Learning [51.59824683232925]
This paper introduces DiGGR (Disentangled Generative Graph Representation Learning), a self-supervised learning framework.
It aims to learn latent disentangled factors and utilize them to guide graph mask modeling.
Experiments on 11 public datasets for two different graph learning tasks demonstrate that DiGGR consistently outperforms many previous self-supervised methods.
arXiv Detail & Related papers (2024-08-24T05:13:02Z) - LCReg: Long-Tailed Image Classification with Latent Categories based
Recognition [81.5551335554507]
We propose the Latent Categories based long-tail Recognition (LCReg) method.
Our hypothesis is that common latent features shared by head and tail classes can be used to improve feature representation.
Specifically, we learn a set of class-agnostic latent features shared by both head and tail classes, and then use semantic data augmentation on the latent features to implicitly increase the diversity of the training sample.
arXiv Detail & Related papers (2023-09-13T02:03:17Z) - Towards Long-Tailed Recognition for Graph Classification via
Collaborative Experts [10.99232053983369]
We propose a novel long-tailed graph-level classification framework via Collaborative Multi-expert Learning (CoMe)
To equilibrate the contributions of head and tail classes, we first develop balanced contrastive learning from the view of representation learning.
We execute gated fusion and disentangled knowledge distillation among the multiple experts to promote the collaboration in a multi-expert framework.
arXiv Detail & Related papers (2023-08-31T10:12:32Z) - Improving GANs for Long-Tailed Data through Group Spectral
Regularization [51.58250647277375]
We propose a novel group Spectral Regularizer (gSR) that prevents the spectral explosion alleviating mode collapse.
We find that gSR effectively combines with existing augmentation and regularization techniques, leading to state-of-the-art image generation performance on long-tailed data.
arXiv Detail & Related papers (2022-08-21T17:51:05Z) - Long-tailed Recognition by Learning from Latent Categories [70.6272114218549]
We introduce a Latent Categories based long-tail Recognition (LCReg) method.
Specifically, we learn a set of class-agnostic latent features shared among the head and tail classes.
Then, we implicitly enrich the training sample diversity via applying semantic data augmentation to the latent features.
arXiv Detail & Related papers (2022-06-02T12:19:51Z) - Improving Tail-Class Representation with Centroid Contrastive Learning [145.73991900239017]
We propose interpolative centroid contrastive learning (ICCL) to improve long-tailed representation learning.
ICCL interpolates two images from a class-agnostic sampler and a class-aware sampler, and trains the model such that the representation of the ICCL can be used to retrieve the centroids for both source classes.
Our result shows a significant accuracy gain of 2.8% on the iNaturalist 2018 dataset with a real-world long-tailed distribution.
arXiv Detail & Related papers (2021-10-19T15:24:48Z) - Graph Contrastive Learning with Adaptive Augmentation [23.37786673825192]
We propose a novel graph contrastive representation learning method with adaptive augmentation.
Specifically, we design augmentation schemes based on node centrality measures to highlight important connective structures.
Our proposed method consistently outperforms existing state-of-the-art baselines and even surpasses some supervised counterparts.
arXiv Detail & Related papers (2020-10-27T15:12:21Z)
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.