The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis

09/15/2020
by   Haiyang Yu, et al.
0

Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance. Existing solutions usually address this issue via class-balancing strategies, e.g., data re-sampling and loss re-weighting, but all these methods adhere to the schema of entangling learning of the representation and classifier. In this study, we conduct an in-depth empirical investigation into the long-tailed problem and found that pre-trained models with instance-balanced sampling already capture the well-learned representations for all classes; moreover, it is possible to achieve better long-tailed classification ability at low cost by only adjusting the classifier. Inspired by this observation, we propose a robust classifier with attentive relation routing, which assigns soft weights by automatically aggregating the relations. Extensive experiments on two datasets demonstrate the effectiveness of our proposed approach. Code and datasets are available in https://github.com/zjunlp/deepke.

READ FULL TEXT
research
10/21/2019

Decoupling Representation and Classifier for Long-Tailed Recognition

The long-tail distribution of the visual world poses great challenges fo...
research
06/12/2023

Feature Fusion from Head to Tail: an Extreme Augmenting Strategy for Long-Tailed Visual Recognition

The imbalanced distribution of long-tailed data poses a challenge for de...
research
12/29/2021

Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification

We address the overlooked unbiasedness in existing long-tailed classific...
research
05/01/2021

GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition

The problem of long-tailed recognition, where the number of examples per...
research
04/20/2021

A novel three-stage training strategy for long-tailed classification

The long-tailed distribution datasets poses great challenges for deep le...
research
12/05/2019

BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

Our work focuses on tackling the challenging but natural visual recognit...
research
05/11/2022

Making Pre-trained Language Models Good Long-tailed Learners

Prompt-tuning has shown appealing performance in few-shot classification...

Please sign up or login with your details

Forgot password? Click here to reset