Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification

by   Kirill Prokofiev, et al.

Multi-label image classification allows predicting a set of labels from a given image. Unlike multiclass classification, where only one label per image is assigned, such setup is applicable for a broader range of applications. In this work we revisit two popular approaches to multilabel classification: transformer-based heads and labels relations information graph processing branches. Although transformer-based heads are considered to achieve better results than graph-based branches, we argue that with the proper training strategy graph-based methods can demonstrate just a small accuracy drop, while spending less computational resources on inference. In our training strategy, instead of Asymmetric Loss (ASL), which is the de-facto standard for multilabel classification, we introduce its modification acting in the angle space. It implicitly learns a proxy feature vector on the unit hypersphere for each class, providing a better discrimination ability, than binary cross entropy loss does on unnormalized features. With the proposed loss and training strategy, we obtain SOTA results among single modality methods on widespread multilabel classification benchmarks such as MS-COCO, PASCAL-VOC, NUS-Wide and Visual Genome 500. Source code of our method is available as a part of the OpenVINO Training Extensions


page 1

page 2

page 3

page 4


MlTr: Multi-label Classification with Transformer

The task of multi-label image classification is to recognize all the obj...

General Multi-label Image Classification with Transformers

Multi-label image classification is the task of predicting a set of labe...

Query2Label: A Simple Transformer Way to Multi-Label Classification

This paper presents a simple and effective approach to solving the multi...

Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets

We present a new loss function called Distribution-Balanced Loss for the...

HyP^2 Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval

Image retrieval has become an increasingly appealing technique with broa...

Analysis and Optimization of Loss Functions for Multiclass, Top-k, and Multilabel Classification

Top-k error is currently a popular performance measure on large scale im...

Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains

This paper proposes an adaptive graph-based approach for multi-label ima...

Please sign up or login with your details

Forgot password? Click here to reset