Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the likelihood of $\log{p}\left(y\mid{x}\right)$ directly can be harmful. Assume for a small constant $\epsilon$, the training set label $y$ is correct with probability $1-\epsilon$ and incorrect otherwise. Label Smoothing regularizes a model based on a softmax with $k$ output values by replacing the hard $0$ and $1$ classification targets with targets of $\frac{\epsilon}{k-1}$ and $1-\epsilon$ respectively.
Source: Deep Learning, Goodfellow et al
Image Source: When Does Label Smoothing Help?
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Language Modelling | 52 | 6.54% |
Decoder | 35 | 4.40% |
Large Language Model | 23 | 2.89% |
Question Answering | 22 | 2.77% |
Semantic Segmentation | 22 | 2.77% |
Object Detection | 17 | 2.14% |
Retrieval | 15 | 1.89% |
Sentence | 15 | 1.89% |
Image Classification | 13 | 1.64% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |