Distribution Alignment: A Unified Framework for Long-tail Visual Recognition

03/30/2021
by   Songyang Zhang, et al.
20

Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the two-stage learning framework via ablative study. Motivated by our discovery, we propose a unified distribution alignment strategy for long-tail visual recognition. Specifically, we develop an adaptive calibration function that enables us to adjust the classification scores for each data point. We then introduce a generalized re-weight method in the two-stage learning to balance the class prior, which provides a flexible and unified solution to diverse scenarios in visual recognition tasks. We validate our method by extensive experiments on four tasks, including image classification, semantic segmentation, object detection, and instance segmentation. Our approach achieves the state-of-the-art results across all four recognition tasks with a simple and unified framework. The code and models will be made publicly available at: https://github.com/Megvii-BaseDetection/DisAlign

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/23/2020

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Most existing object instance detection and segmentation models only wor...
research
10/30/2022

SL3D: Self-supervised-Self-labeled 3D Recognition

There are a lot of promising results in 3D recognition, including classi...
research
12/03/2022

VLG: General Video Recognition with Web Textual Knowledge

Video recognition in an open and dynamic world is quite challenging, as ...
research
05/06/2021

Multi-Perspective LSTM for Joint Visual Representation Learning

We present a novel LSTM cell architecture capable of learning both intra...
research
10/29/2019

Classification Calibration for Long-tail Instance Segmentation

Remarkable progress has been made in object instance detection and segme...
research
12/18/2022

Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization

Domain shift widely exists in the visual world, while modern deep neural...
research
07/23/2020

Funnel Activation for Visual Recognition

We present a conceptually simple but effective funnel activation for ima...

Please sign up or login with your details

Forgot password? Click here to reset