DeepAI AI Chat
Log In Sign Up

Multi-label Iterated Learning for Image Classification with Label Ambiguity

by   Sai Rajeswar, et al.

Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown that datasets like ImageNet are weakly labeled since images with multiple object classes present are assigned a single label. This ambiguity biases models towards a single prediction, which could result in the suppression of classes that tend to co-occur in the data. Inspired by language emergence literature, we propose multi-label iterated learning (MILe) to incorporate the inductive biases of multi-label learning from single labels using the framework of iterated learning. MILe is a simple yet effective procedure that builds a multi-label description of the image by propagating binary predictions through successive generations of teacher and student networks with a learning bottleneck. Experiments show that our approach exhibits systematic benefits on ImageNet accuracy as well as ReaL F1 score, which indicates that MILe deals better with label ambiguity than the standard training procedure, even when fine-tuning from self-supervised weights. We also show that MILe is effective reducing label noise, achieving state-of-the-art performance on real-world large-scale noisy data such as WebVision. Furthermore, MILe improves performance in class incremental settings such as IIRC and it is robust to distribution shifts. Code:


page 5

page 8

page 13


Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels

ImageNet has been arguably the most popular image classification benchma...

Personalizing Pre-trained Models

Self-supervised or weakly supervised models trained on large-scale datas...

Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation Learning

In existing visual representation learning tasks, deep convolutional neu...

How Does Heterogeneous Label Noise Impact Generalization in Neural Nets?

Incorrectly labeled examples, or label noise, is common in real-world co...

When does dough become a bagel? Analyzing the remaining mistakes on ImageNet

Image classification accuracy on the ImageNet dataset has been a baromet...

Multi-label Pixelwise Classification for Reconstruction of Large-scale Urban Areas

Object classification is one of the many holy grails in computer vision ...

Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers

Disaggregated performance metrics across demographic groups are a hallma...