CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images

08/03/2018
by   Sheng Guo, et al.
0

We present a simple yet efficient approach capable of training deep neural networks on large-scale weakly-supervised web images, which are crawled rawly from the Internet by using text queries, without any human annotation. We develop a principled learning strategy by leveraging curriculum learning, with the goal of handling massive amount of noisy labels and data imbalance effectively. We design a new learning curriculum by measuring the complexity of data using its distribution density in a feature space, and rank the complexity in an unsupervised manner. This allows for an efficient implementation of curriculum learning on large-scale web images, resulting in a high-performance CNN model, where the negative impact of noisy labels is reduced substantially. Importantly, we show by experiments that those images with highly noisy labels can surprisingly improve the generalization capability of model, by serving as a manner of regularization. Our approaches obtain the state-of-the-art performance on four benchmarks, including Webvision, ImageNet, Clothing-1M and Food-101. With an ensemble of multiple models, we achieve a top-5 error rate of 5.2 top performance that surpasses other results by a large margin of about 50 relative error rate. Codes and models are available at: https://github.com/guoshengcv/CurriculumNet.

READ FULL TEXT
research
08/25/2020

Weakly Supervised Learning with Side Information for Noisy Labeled Images

In many real-world datasets, like WebVision, the performance of DNN base...
research
11/30/2016

Attend in groups: a weakly-supervised deep learning framework for learning from web data

Large-scale datasets have driven the rapid development of deep neural ne...
research
02/08/2018

A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels

The recent success of deep neural networks is powered in part by large-s...
research
04/17/2019

Guided Anisotropic Diffusion and Iterative Learning for Weakly Supervised Change Detection

Large scale datasets created from user labels or openly available data h...
research
05/07/2015

Webly Supervised Learning of Convolutional Networks

We present an approach to utilize large amounts of web data for learning...
research
05/15/2023

CLIP-VG: Self-paced Curriculum Adapting of CLIP via Exploiting Pseudo-Language Labels for Visual Grounding

Visual Grounding (VG) refers to locating a region described by expressio...
research
12/15/2022

Curriculum Learning Meets Weakly Supervised Modality Correlation Learning

In the field of multimodal sentiment analysis (MSA), a few studies have ...

Please sign up or login with your details

Forgot password? Click here to reset