Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation

05/23/2022
by   Jiazhi Xu, et al.
18

Multi-Label Image Classification (MLIC) approaches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook discriminative features of the target itself and lead to model overfitting, thus undermining the performance. In this study, we propose a generic framework named Parallel Self-Distillation (PSD) for boosting MLIC models. PSD decomposes the original MLIC task into several simpler MLIC sub-tasks via two elaborated complementary task decomposition strategies named Co-occurrence Graph Partition (CGP) and Dis-occurrence Graph Partition (DGP). Then, the MLIC models of fewer categories are trained with these sub-tasks in parallel for respectively learning the joint patterns and the category-specific patterns of labels. Finally, knowledge distillation is leveraged to learn a compact global ensemble of full categories with these learned patterns for reconciling the label correlation exploitation and model overfitting. Extensive results on MS-COCO and NUS-WIDE datasets demonstrate that our framework can be easily plugged into many MLIC approaches and improve performances of recent state-of-the-art approaches. The explainable visual study also further validates that our method is able to learn both the category-specific and co-occurring features. The source code is released at https://github.com/Robbie-Xu/CPSD.

READ FULL TEXT

page 1

page 3

page 6

research
09/16/2018

Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection

Multi-label image classification is a fundamental but challenging task t...
research
03/15/2023

Knowledge Distillation from Single to Multi Labels: an Empirical Study

Knowledge distillation (KD) has been extensively studied in single-label...
research
12/02/2021

A Fast Knowledge Distillation Framework for Visual Recognition

While Knowledge Distillation (KD) has been recognized as a useful tool i...
research
05/10/2023

Explainable Knowledge Distillation for On-device Chest X-Ray Classification

Automated multi-label chest X-rays (CXR) image classification has achiev...
research
08/20/2019

Learning Semantic-Specific Graph Representation for Multi-Label Image Recognition

Recognizing multiple labels of images is a practical and challenging tas...
research
01/09/2020

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

Existing models often leverage co-occurrences between objects and their ...
research
07/18/2023

PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image Classification

Multi-label image classification is a prediction task that aims to ident...

Please sign up or login with your details

Forgot password? Click here to reset