Learning to Segment the Tail
- URL: http://arxiv.org/abs/2004.00900v2
- Date: Fri, 3 Apr 2020 03:27:08 GMT
- Title: Learning to Segment the Tail
- Authors: Xinting Hu, Yi Jiang, Kaihua Tang, Jingyuan Chen, Chunyan Miao,
Hanwang Zhang
- Abstract summary: Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data.
We propose a "divide&conquer" strategy for the challenging LVIS task: divide the whole data into balanced parts and then apply incremental learning to conquer each one.
- Score: 91.38061765836443
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Real-world visual recognition requires handling the extreme sample imbalance
in large-scale long-tailed data. We propose a "divide&conquer" strategy for the
challenging LVIS task: divide the whole data into balanced parts and then apply
incremental learning to conquer each one. This derives a novel learning
paradigm: class-incremental few-shot learning, which is especially effective
for the challenge evolving over time: 1) the class imbalance among the
old-class knowledge review and 2) the few-shot data in new-class learning. We
call our approach Learning to Segment the Tail (LST). In particular, we design
an instance-level balanced replay scheme, which is a memory-efficient
approximation to balance the instance-level samples from the old-class images.
We also propose to use a meta-module for new-class learning, where the module
parameters are shared across incremental phases, gaining the learning-to-learn
knowledge incrementally, from the data-rich head to the data-poor tail. We
empirically show that: at the expense of a little sacrifice of head-class
forgetting, we can gain a significant 8.3% AP improvement for the tail classes
with less than 10 instances, achieving an overall 2.0% AP boost for the whole
1,230 classes.
Related papers
- Towards Non-Exemplar Semi-Supervised Class-Incremental Learning [33.560003528712414]
Class-incremental learning aims to gradually recognize new classes while maintaining the discriminability of old ones.
We propose a non-exemplar semi-supervised CIL framework with contrastive learning and semi-supervised incremental prototype classifier (Semi-IPC)
Semi-IPC learns a prototype for each class with unsupervised regularization, enabling the model to incrementally learn from partially labeled new data.
arXiv Detail & Related papers (2024-03-27T06:28:19Z) - Robust Feature Learning and Global Variance-Driven Classifier Alignment
for Long-Tail Class Incremental Learning [20.267257778779992]
This paper introduces a two-stage framework designed to enhance long-tail class incremental learning.
We address the challenge posed by the under-representation of tail classes in long-tail class incremental learning.
The proposed framework can seamlessly integrate as a module with any class incremental learning method.
arXiv Detail & Related papers (2023-11-02T13:28:53Z) - Neural Collapse Terminus: A Unified Solution for Class Incremental
Learning and Its Variants [166.916517335816]
In this paper, we offer a unified solution to the misalignment dilemma in the three tasks.
We propose neural collapse terminus that is a fixed structure with the maximal equiangular inter-class separation for the whole label space.
Our method holds the neural collapse optimality in an incremental fashion regardless of data imbalance or data scarcity.
arXiv Detail & Related papers (2023-08-03T13:09:59Z) - Class-Incremental Learning: A Survey [84.30083092434938]
Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally.
CIL tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades.
We provide a rigorous and unified evaluation of 17 methods in benchmark image classification tasks to find out the characteristics of different algorithms.
arXiv Detail & Related papers (2023-02-07T17:59:05Z) - MoBYv2AL: Self-supervised Active Learning for Image Classification [57.4372176671293]
We present MoBYv2AL, a novel self-supervised active learning framework for image classification.
Our contribution lies in lifting MoBY, one of the most successful self-supervised learning algorithms, to the AL pipeline.
We achieve state-of-the-art results when compared to recent AL methods.
arXiv Detail & Related papers (2023-01-04T10:52:02Z) - Self-Supervised Class Incremental Learning [51.62542103481908]
Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels.
When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new.
In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time.
arXiv Detail & Related papers (2021-11-18T06:58:19Z) - Few-Shot Incremental Learning with Continually Evolved Classifiers [46.278573301326276]
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points.
The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems.
We propose a Continually Evolved CIF ( CEC) that employs a graph model to propagate context information between classifiers for adaptation.
arXiv Detail & Related papers (2021-04-07T10:54:51Z) - Class-incremental Learning with Rectified Feature-Graph Preservation [24.098892115785066]
A central theme of this paper is to learn new classes that arrive in sequential phases over time.
We propose a weighted-Euclidean regularization for old knowledge preservation.
We show how it can work with binary cross-entropy to increase class separation for effective learning of new classes.
arXiv Detail & Related papers (2020-12-15T07:26:04Z) - iTAML: An Incremental Task-Agnostic Meta-learning Approach [123.10294801296926]
Humans can continuously learn new knowledge as their experience grows.
Previous learning in deep neural networks can quickly fade out when they are trained on a new task.
We introduce a novel meta-learning approach that seeks to maintain an equilibrium between all encountered tasks.
arXiv Detail & Related papers (2020-03-25T21:42:48Z) - Cognitively-Inspired Model for Incremental Learning Using a Few Examples [11.193504036335503]
Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes.
Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally, while most incremental learning approaches require a large amount of training data per class.
We propose a novel approach inspired by the concept learning model of the hippocampus and the neocortex that represents each image class as centroids.
arXiv Detail & Related papers (2020-02-27T19:52:42Z)
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.