Boosting High Resolution Image Classification with Scaling-up Transformers
This work addresses image classification for nutrient deficiency detection, but it is incremental as it combines existing techniques without introducing fundamentally new methods.
The authors tackled high-resolution image classification by developing a holistic pipeline that won second place in the ICCV/CVPPA2023 Deep Nutrient Deficiency Challenge, achieving competitive results through methods like scaling up transformers and data augmentation.
We present a holistic approach for high resolution image classification that won second place in the ICCV/CVPPA2023 Deep Nutrient Deficiency Challenge. The approach consists of a full pipeline of: 1) data distribution analysis to check potential domain shift, 2) backbone selection for a strong baseline model that scales up for high resolution input, 3) transfer learning that utilizes published pretrained models and continuous fine-tuning on small sub-datasets, 4) data augmentation for the diversity of training data and to prevent overfitting, 5) test-time augmentation to improve the prediction's robustness, and 6) "data soups" that conducts cross-fold model prediction average for smoothened final test results.