Related papers: Highly Constrained Coded Aperture Imaging Systems …
Coded-illumination can enable quantitative phase microscopy of transparent samples with minimal hardware requirements. Intensity images are captured with different source patterns and a non-linear phase retrieval optimization reconstructs…
Knowledge distillation (KD) has been recognized as an effective tool to compress and accelerate models. However, current KD approaches generally suffer from an accuracy drop and/or an excruciatingly long distillation process. In this paper,…
It has been revealed that efficient dense image prediction (EDIP) models designed for AI chips, trained using the knowledge distillation (KD) framework, encounter two key challenges, including \emph{maintaining boundary region completeness}…
Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter…
Snapshot Compressed Imaging (SCI) offers high-speed, low-bandwidth, and energy-efficient image acquisition, but remains challenged by low-light and low signal-to-noise ratio (SNR) conditions. Moreover, practical hardware constraints in…
We study data-free knowledge distillation (KD) for monocular depth estimation (MDE), which learns a lightweight model for real-world depth perception tasks by compressing it from a trained teacher model while lacking training data in the…
We present Curve Distillation, CuDi, for efficient and controllable exposure adjustment without the requirement of paired or unpaired data during training. Our method inherits the zero-reference learning and curve-based framework from an…
Current deep learning-based low-light image enhancement methods often struggle with high-resolution images, and fail to meet the practical demands of visual perception across diverse and unseen scenarios. In this paper, we introduce a novel…
Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…
High-dimensional imaging technology has demonstrated significant research value across diverse fields, including environmental monitoring, agricultural inspection, and biomedical imaging, through integrating spatial (X*Y), spectral, and…
Online High-Definition (HD) map construction is a key component of autonomous driving. Recent methods rely on multi-view camera images for cost-effective HD map segmentation, but cameras lack depth information for accurate scene geometry.…
Knowledge Distillation (KD) is a widespread technique for compressing the knowledge of large models into more compact and efficient models. KD has proved to be highly effective in building well-performing low-complexity Acoustic Scene…
Significant improvement has been achieved in automated audio captioning (AAC) with recent models. However, these models have become increasingly large as their performance is enhanced. In this work, we propose a knowledge distillation (KD)…
Speech denoising is a generally adopted and impactful task, appearing in many common and everyday-life use cases. Although there are very powerful methods published, most of those are too complex for deployment in everyday and low-resources…
With the rapid development of artificial intelligence (AI), especially in the medical field, the need for its explainability has grown. In medical image analysis, a high degree of transparency and model interpretability can help clinicians…
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…
Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the…
Hyperspectral imaging, capturing detailed spectral information for each pixel, is pivotal in diverse scientific and industrial applications. Yet, the acquisition of high-resolution (HR) hyperspectral images (HSIs) often needs to be…
Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively…
Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficiency remains a…