Related papers: LGSQE: Lightweight Generated Sample Quality Evalua…

In this paper, we present a general method that can improve the sample quality of pre-trained likelihood based generative models. Our method constructs an energy function on the latent variable space that yields an energy function on…

Building of data for quality estimation (QE) training is expensive and requires significant human labor. In this study, we focus on a data-centric approach while performing QE, and subsequently propose a fully automatic pseudo-QE dataset…

Score-based generative models (SGMs) have recently demonstrated impressive results in terms of both sample quality and distribution coverage. However, they are usually applied directly in data space and often require thousands of network…

Label-noise or curated unlabeled data is used to compensate for the assumption of clean labeled data in training the conditional generative adversarial network; however, satisfying such an extended assumption is occasionally laborious or…

Scarcity of labeled data is a bottleneck for supervised learning models. A paradigm that has evolved for dealing with this problem is data programming. An existing data programming paradigm allows human supervision to be provided as a set…

Finding relevant and high-quality datasets to train machine learning models is a major bottleneck for practitioners. Furthermore, to address ambitious real-world use-cases there is usually the requirement that the data come labelled with…

In the realm of deep neural network deployment, low-bit quantization presents a promising avenue for enhancing computational efficiency. However, it often hinges on the availability of training data to mitigate quantization errors, a…

Current state-of-the-art Quality Estimation (QE) in machine translation relies on massive, proprietary LLMs, raising data privacy concerns. We demonstrate that smaller, open-source LLMs (<30B parameters) are a viable, cost-effective and…

Generative adversarial networks (GANs) have achieved impressive results today, but not all generated images are perfect. A number of quantitative criteria have recently emerged for generative model, but none of them are designed for a…

The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process…

Predicting drop coalescence based on process parameters is crucial for experiment design in chemical engineering. However, predictive models can suffer from the lack of training data and more importantly, the label imbalance problem. In…

Learning with noisy labels (LNL) aims to ensure model generalization given a label-corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine-grained datasets (LNL-FG), which is more practical and…

Label quality issues, such as noisy labels and imbalanced class distributions, have negative effects on model performance. Automatic reweighting methods identify problematic samples with label quality issues by recognizing their negative…

Discrete image tokenization is a key bottleneck for scalable visual generation: a tokenizer must remain compact for efficient latent-space priors while preserving semantic structure and using discrete capacity effectively. Existing…

Recently, label distribution learning (LDL) has drawn much attention in machine learning, where LDL model is learned from labelel instances. Different from single-label and multi-label annotations, label distributions describe the instance…

We consider a measurement constrained supervised learning problem, that is, (1) full sample of the predictors are given; (2) the response observations are unavailable and expensive to measure. Thus, it is ideal to select a subsample of…

In this work, we explore a useful but often neglected methodology for robustness analysis of text generation evaluation metrics: stress tests with synthetic data. Basically, we design and synthesize a wide range of potential errors and…

Exploring and mining subtle yet distinctive features between sub-categories with similar appearances is crucial for fine-grained visual categorization (FGVC). However, less effort has been devoted to assessing the quality of extracted…

Quality of Experience (QoE) prediction plays a crucial role in optimizing resource management and enhancing user satisfaction across both telecommunication and OTT services. While recent advances predominantly rely on deep learning models,…

A major limitation of prompt tuning is its dependence on large labeled training datasets. Under few-shot learning settings, prompt tuning lags far behind full-model fine-tuning, limiting its scope of application. In this paper, we leverage…