相关论文: Embedding-Driven Data Distillation for 360-Degree …

Semantic segmentation benchmarks in the realm of autonomous driving are dominated by large pre-trained transformers, yet their widespread adoption is impeded by substantial computational costs and prolonged training durations. To lift this…

Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ…

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent perceptual IR algorithms based on generative adversarial networks (GANs) have brought in significant improvement…

Incremental learning targets at achieving good performance on new categories without forgetting old ones. Knowledge distillation has been shown critical in preserving the performance on old classes. Conventional methods, however,…

In modern process industries, data-driven models are important tools for real-time monitoring when key performance indicators are difficult to measure directly. While accurate predictions are essential, reliable uncertainty quantification…

Image quality assessment (IQA) is a fundamental metric for image processing tasks (e.g., compression). With full-reference IQAs, traditional IQAs, such as PSNR and SSIM, have been used. Recently, IQAs based on deep neural networks (deep…

We present IQA-Spider, the first image quality assessment (IQA) framework that unifies reasoning, grounding, and referring into a single LMM-based framework for multi-granularity quality understanding. Existing LMM-based IQA methods…

Dataset distillation has emerged as a strategy to compress real-world datasets for efficient training. However, it struggles with large-scale and high-resolution datasets, limiting its practicality. This paper introduces a novel…

Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they are typically complex, heavyweight, and require substantial…

Recent years have witnessed remarkable achievements in perceptual image restoration (IR), creating an urgent demand for accurate image quality assessment (IQA), which is essential for both performance comparison and algorithm optimization.…

We introduce Principal Component Analysis guided Quantile Sampling (PCA QS), a novel sampling framework designed to preserve both the statistical and geometric structure of large scale datasets. Unlike conventional PCA, which reduces…

Deep learning methods for image quality assessment (IQA) are limited due to the small size of existing datasets. Extensive datasets require substantial resources both for generating publishable content and annotating it accurately. We…

Video Quality Assessment (VQA) aims to evaluate video quality based on perceptual distortions and human preferences. Despite the promising performance of existing methods using Convolutional Neural Networks (CNNs) and Vision Transformers…

Contemporary no-reference image quality assessment (NR-IQA) models can effectively quantify perceived image quality, often achieving strong correlations with human perceptual scores on standard IQA benchmarks. Yet, limited efforts have been…

Image quality that is consistent with human opinion is assessed by a perceptual image quality assessment (IQA) that defines/utilizes a computational model. A good model should take effectiveness and efficiency into consideration, but most…

Deep ensembles excel in large-scale image classification tasks both in terms of prediction accuracy and calibration. Despite being simple to train, the computation and memory cost of deep ensembles limits their practicability. While some…

Knowledge distillation has emerged as a highly effective method for bridging the representation discrepancy between large-scale models and lightweight models. Prevalent approaches involve leveraging appropriate metrics to minimize the…

Dataset distillation has gained significant interest in recent years, yet existing approaches typically distill from the entire dataset, potentially including non-beneficial samples. We introduce a novel "Prune First, Distill After"…

The joint utilization of diverse data sources for medical imaging segmentation has emerged as a crucial area of research, aiming to address challenges such as data heterogeneity, domain shift, and data quality discrepancies. Integrating…

Continuous machine learning pipelines are common in industrial settings where models are periodically trained on data streams. Unfortunately, concept drifts may occur in data streams where the joint distribution of the data X and label y,…