Related papers: LightBSR: Towards Lightweight Blind Super-Resoluti…
Single-Image-Super-Resolution (SISR) is a classical computer vision problem that has benefited from the recent advancements in deep learning methods, especially the advancements of convolutional neural networks (CNN). Although…
Numerous image superresolution (SR) algorithms have been proposed for reconstructing high-resolution (HR) images from input images with lower spatial resolutions. However, effectively evaluating the perceptual quality of SR images remains a…
Multilingual self-supervised speech representation models have greatly enhanced the speech recognition performance for low-resource languages, and the compression of these huge models has also become a crucial prerequisite for their…
Fast and accurate object perception in low-light traffic scenes has attracted increasing attention. However, due to severe illumination degradation and the lack of reliable visual cues, existing perception models and methods struggle to…
The use of episodic memory in continual learning has demonstrated effectiveness for alleviating catastrophic forgetting. In recent studies, gradient-based approaches have been developed to make more efficient use of compact episodic memory.…
In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks. Our method, called…
Recent advances in implicit neural representations and differentiable rendering make it possible to simultaneously recover the geometry and materials of an object from multi-view RGB images captured under unknown static illumination.…
Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a…
Neural retrievers based on dense representations combined with Approximate Nearest Neighbors search have recently received a lot of attention, owing their success to distillation and/or better sampling of examples for training -- while…
Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…
Infrared image super-resolution (IISR) under real-world conditions is a practically significant yet rarely addressed task. Pioneering works are often trained and evaluated on simulated datasets or neglect the intrinsic differences between…
Recent efforts have witnessed remarkable progress in Satellite Video Super-Resolution (SVSR). However, most SVSR methods usually assume the degradation is fixed and known, e.g., bicubic downsampling, which makes them vulnerable in…
Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to specific scenarios, while unsupervised methods, though…
Knowledge Distillation (KD) is a fundamental technique for compressing large language models (LLMs) into compact, efficient student models. However, existing white-box KD methods mainly focus on balancing ground truth and student-generated…
This work presents a lightweight super-resolution (LiteSR) neural network for depth and intensity images acquired from a consumer-grade single-photon avalanche diode (SPAD) array with a 48x32 spatial resolution. The proposed framework…
Recent research on deep convolutional neural networks (CNNs) has provided a significant performance boost on efficient super-resolution (SR) tasks by trading off the performance and applicability. However, most existing methods focus on…
Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data privacy concerns, missing data modalities are common in…
Blind face restoration (BFR) is a highly challenging problem due to the uncertainty of data degradation patterns. Current BFR methods have realized certain restored productions but with inherent neural degradations that limit real-world…
Implicit Neural Representation (INR) is an innovative approach for representing complex shapes or objects without explicitly defining their geometry or surface structure. Instead, INR represents objects as continuous functions. Previous…
Large language models (LLMs) have demonstrated remarkable abilities in various natural language processing areas, but they demand high computation resources which limits their deployment in real-world. Distillation is one technique to solve…