Related papers: Automated Synthetic-to-Real Generalization

Synthetic data has gained attention for training large language models, but poor-quality data can harm performance (see, e.g., Shumailov et al. (2023); Seddik et al. (2024)). A potential solution is data pruning, which retains only…

We investigate the potential of learning visual representations using synthetic images generated by text-to-image models. This is a natural question in the light of the excellent performance of such models in generating high-quality images.…

The rapid progress in machine learning models has significantly boosted the potential for real-world applications such as autonomous vehicles, disease diagnoses, and recognition of emergencies. The performance of many machine learning…

Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been…

Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…

The rapid advancement of generative models, such as Stable Diffusion, raises a key question: how can synthetic data from these models enhance predictive modeling? While they can generate vast amounts of datasets, only a subset meaningfully…

Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples. To employ large models for FGVC without suffering from overfitting, existing…

World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel inputs) has become…

Image-to-image translation is the recent trend to transform images from one domain to another domain using generative adversarial network (GAN). The existing GAN models perform the training by only utilizing the input and output modalities…

The need for large amounts of training and validation data is a huge concern in scaling AI algorithms for autonomous driving. Semantic Image Synthesis (SIS), or label-to-image translation, promises to address this issue by translating…

We question the dominant role of real-world training images in the field of material classification by investigating whether synthesized data can generalise more effectively than real-world data. Experimental results on three challenging…

Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an approach to aligning superhuman AI systems. Existing theoretical analyses either fix the…

The goal of data attribution for text-to-image models is to identify the training images that most influence the generation of a new image. Influence is defined such that, for a given output, if a model is retrained from scratch without the…

Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide…

In the field of deep learning applied to face recognition, securing large-scale, high-quality datasets is vital for attaining precise and reliable results. However, amassing significant volumes of high-quality real data faces hurdles such…

Image-to-image (i2i) networks struggle to capture local changes because they do not affect the global scene structure. For example, translating from highway scenes to offroad, i2i networks easily focus on global color features but ignore…

One of the biggest challenges in machine learning is data collection. Training data is an important part since it determines how the model will behave. In object classification, capturing a large number of images per object and in different…

Deep learning models frequently suffer from various problems such as class imbalance and lack of robustness to distribution shift. It is often difficult to find data suitable for training beyond the available benchmarks. This is especially…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

We propose LayerSync, a domain-agnostic approach for improving the generation quality and the training efficiency of diffusion models. Prior studies have highlighted the connection between the quality of generation and the representations…