The reviewed record of science sign in
Pith

arxiv: 2311.15200 · v1 · pith:ILPLY7RI · submitted 2023-11-26 · cs.CV · cs.LG

SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification

Reviewed by Pithpith:ILPLY7RIopen to challenge →

classification cs.CV cs.LG
keywords imagessplicemiximagemethodsmulti-labelspliceaugmentationclassification
0
0 comments X
read the original abstract

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies between single- and multi-label images, i.e., a multi-label image involves multiple co-occurred categories and fickle object scales. On the other hand, previous multi-label image classification (MLIC) methods tend to design elaborate models, bringing expensive computation. In this paper, we introduce a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix. The "splice" in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias; 2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together. Furthermore, such splice in our SpliceMixed mini-batch enables interactions between mixed images and original regular images. We also offer a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the flexible extensibility of our SpliceMix. Extensive experiments on various tasks demonstrate that only using SpliceMix with a baseline model (e.g., ResNet) achieves better performance than state-of-the-art methods. Moreover, the generalizability of our SpliceMix is further validated by the improvements in current MLIC methods when married with our SpliceMix. The code is available at https://github.com/zuiran/SpliceMix.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.