相关论文: Training Data Provenance Verification: Did Your Mo…

In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of…

Synthetic data algorithms are widely employed in industries to generate artificial data for downstream learning tasks. While existing research primarily focuses on empirically evaluating utility of synthetic data, its theoretical…

Enabling image generation models to be spatially controlled is an important area of research, empowering users to better generate images according to their own fine-grained specifications via e.g. edge maps, poses. Although this task has…

Current methods for reconstructing training data from trained classifiers are restricted to very small models, limited training set sizes, and low-resolution images. Such restrictions hinder their applicability to real-world scenarios. In…

It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are…

Training data plays a crucial role in Large Language Models (LLM) scaling, yet high quality data is of limited supply. Synthetic data techniques offer a potential path toward sidestepping these limitations. We conduct a large-scale…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Photorealistic image generation has reached a new level of quality due to the breakthroughs of generative adversarial networks (GANs). Yet, the dark side of such deepfakes, the malicious use of generated media, raises concerns about visual…

Quantization is a widely adopted technique for deep neural networks to reduce the memory and computational resources required. However, when quantized, most models would need a suitable calibration process to keep their performance intact,…

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…

Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions. This seemingly implies that high-performing models share similar biases regardless of training…

Recently, an extensive amount of research has been focused on compressing and accelerating Deep Neural Networks (DNN). So far, high compression rate algorithms require part of the training dataset for a low precision calibration, or a…

Handwritten Text Recognition has achieved an impressive performance in public benchmarks. However, due to the high inter- and intra-class variability between handwriting styles, such recognizers need to be trained using huge volumes of…

Generative diffusion models, including Stable Diffusion and Midjourney, can generate visually appealing, diverse, and high-resolution images for various applications. These models are trained on billions of internet-sourced images, raising…

The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's…

This paper extensively investigates the effectiveness of synthetic training data to improve the capabilities of vision-and-language models for grounding textual descriptions to image regions. We explore various strategies to best generate…

Text-to-image diffusion models are pushing the boundaries of what generative AI can achieve in our lives. Beyond their ability to generate general images, new personalization techniques have been proposed to customize the pre-trained base…

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification…

High complexity models are notorious in machine learning for overfitting, a phenomenon in which models well represent data but fail to generalize an underlying data generating process. A typical procedure for circumventing overfitting…

Pre-training models on Imagenet or other massive datasets of real images has led to major advances in computer vision, albeit accompanied with shortcomings related to curation cost, privacy, usage rights, and ethical issues. In this paper,…