Replicate – Run open-source machine learning models with a cloud API
We propose a data augmentation strategy, named DFM-X, that leverages knowledge about frequency shortcuts, encoded in Dominant Frequencies Maps computed for image classification models.
Neural networks are prone to learn easy solutions from superficial statistics in the data, namely shortcut learning, which impairs generalization and robustness of models. We propose a data augmentation strategy, named DFM-X, that leverages knowledge about frequency shortcuts, encoded in Dominant Frequencies Maps computed for image classification models. We randomly select X% training images of certain classes for augmentation, and process them by retaining the frequencies included in the DFMs of other classes. This strategy compels the models to leverage a broader range of frequencies for classification, rather than relying on specific frequency sets. Thus, the models learn more deep and task-related semantics compared to their counterpart trained with standard setups. Unlike other commonly used augmentation techniques which focus on increasing the visual variations of training data, our method targets exploiting the original data efficiently, by distilling prior knowledge about destructive learning behavior of models from data. Our experimental results demonstrate that DFM-X improves robustness against common corruptions and adversarial attacks. It can be seamlessly integrated with other augmentation techniques to further enhance the robustness of models.
Replicate – Run open-source machine learning models with a cloud API
Google Gemini, a multimodal AI by DeepMind, processes text, audio, images, and more. Gemini outperforms in AI benchmarks, is optimized for varied devices, and has been tested for safety and bias, adhering to responsible AI practices.
LongLLaMA is a large language model designed to handle very long text contexts, up to 256,000 tokens. It's based on OpenLLaMA and uses a technique called Focused Transformer (FoT) for training. The repository provides a smaller 3B version of LongLLaMA for free use. It can also be used as a replacement for LLaMA models with shorter contexts.
LAMA utilizes a reinforcement learning framework combined with a motion matching algorithm. Reinforcement learning helps the model make appropriate decisions in various scenarios, while motion matching algorithms ensure that synthesized actions match real human actions. In addition, LAMA also utilizes the motion editing framework of manifold learning to cover various possible changes in interactions and operations.
Video ReTalking, advanced real-world talking head video according to input audio, producing a high-quality
Then transplant it to the real world to solve complex problems
Quick compare routes for nearby alternatives.
Compare DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning with Replicate-AI model GFPGAN can help restore old photos and jump into the preserved compare route.
Open compare route →Compare DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning with Free Google Gemini: the best largest and most capable AI model and jump into the preserved compare route.
Open compare route →Compare DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning with LongLLaMA-handle very long text contexts, up to 256,000 tokens and jump into the preserved compare route.
Open compare route →