Frank Hutter, Samuel Müller
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Automatic augmentation methods have recently become a crucial pillar for strong model performance in vision tasks. While existing automatic augmentation methods need to trade off simplicity, cost and performance, we present a most simple baseline, TrivialAugment, that outperforms previous methods for almost free. TrivialAugment is parameter-free and only applies a single augmentation to each image. Thus, TrivialAugment's effectiveness is very unexpected to us and we performed very thorough experiments to study its performance. First, we compare Triv-ialAugment to previous state-of-the-art methods in a variety of image classification scenarios. Then, we perform multiple ablation studies with different augmentation spaces, augmentation methods and setups to understand the crucial requirements for its performance. Additionally, we provide a simple interface to facilitate the widespread adoption of automatic augmentation methods, as well as our full code base for reproducibility 1 . Since our work reveals a stagnation in many parts of automatic augmentation research, we end with a short proposal of best practices for sustained future progress in automatic augmentation methods. Sample augmentation and apply it 1.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.10158")
get_code_for_paper("2103.10158")
have("2103.10158")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.10158.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.10158)
Connect an agent — have() is free.