Fill-Up: Balancing Long-Tailed Data with Generative Models
Shin, Joonghyuk, Kang, Minguk, Park, Jaesik
–arXiv.org Artificial Intelligence
Modern text-to-image synthesis models have achieved an exceptional level of photorealism, generating high-quality images from arbitrary text descriptions. In light of the impressive synthesis ability, several studies have exhibited promising results in exploiting generated data for image recognition. However, directly supplementing data-hungry situations in the real-world (e.g. few-shot or long-tailed scenarios) with existing approaches result in marginal performance gains, as they suffer to thoroughly reflect the distribution of the real data. Through extensive experiments, this paper proposes a new image synthesis pipeline for long-tailed situations using Textual Inversion. The study demonstrates that generated images from textual-inverted text tokens effectively aligns with the real domain, significantly enhancing the recognition ability of a standard ResNet50 backbone. We also show that real-world data imbalance scenarios can be successfully mitigated by filling up the imbalanced data with synthetic images. In conjunction with techniques in the area of long-tailed recognition, our method achieves state-of-the-art results on standard long-tailed benchmarks when trained from scratch.
arXiv.org Artificial Intelligence
Jun-12-2023
- Country:
- Africa (0.05)
- Asia
- Middle East > Jordan (0.04)
- South Korea > Gyeongsangbuk-do
- Pohang (0.04)
- Europe > Italy
- Calabria > Catanzaro Province > Catanzaro (0.04)
- Genre:
- Research Report
- New Finding (0.92)
- Promising Solution (0.93)
- Research Report
- Industry:
- Information Technology > Security & Privacy (0.67)
- Leisure & Entertainment > Sports (0.46)
- Media > Photography (0.46)
- Transportation
- Ground (0.46)
- Infrastructure & Services (0.46)
- Technology: