相关论文: Comprehensive Machine Learning Benchmarking for Fr…

Recent advances in artificial intelligence (AI), in particular self-supervised learning of foundation models (FMs), are revolutionizing medical imaging and computational pathology (CPath). A constant challenge in the analysis of digital…

A common problem for composite images is the incompatibility of their foreground and background components. Image harmonization aims to solve this problem, making the whole image look more authentic and coherent. Most existing solutions…

As deep neural networks include a high number of parameters and operations, it can be a challenge to implement these models on devices with limited computational resources. Despite the development of novel pruning methods toward…

Parameter-efficient transfer learning (PETL) is proposed as a cost-effective way to transfer pre-trained models to downstream tasks, avoiding the high cost of updating entire large-scale pre-trained models (LPMs). In this work, we present…

Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak…

Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. Undoubtedly, this task inherits the main challenges from both few-shot learning and fine-grained…

Fabric image retrieval is beneficial to many applications including clothing searching, online shopping and cloth modeling. Learning pairwise image similarity is of great importance to an image retrieval task. With the resurgence of…

Face anti-spoofing (FAS) and face forgery detection play vital roles in securing face biometric systems from presentation attacks (PAs) and vicious digital manipulation (e.g., deepfakes). Despite promising performance upon large-scale data…

This work demonstrates that fine-tuning transforms foundational machine-learned interatomic potentials (MLIPs) to achieve consistent, near-ab initio accuracy across diverse architectures. Benchmarking five leading MLIP frameworks (MACE,…

Federated Learning (FL) enables decentralized, privacy-preserving model training but struggles to balance global generalization and local personalization due to non-identical data distributions across clients. Personalized Fine-Tuning…

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in cross-modal understanding and generation by integrating visual and textual information. While instruction tuning and parameter-efficient fine-tuning methods have…

Prevailing video frame interpolation algorithms, that generate the intermediate frames from consecutive inputs, typically rely on complex model architectures with heavy parameters or large delay, hindering them from diverse real-time…

High-precision scene parsing tasks, including image matting and dichotomous segmentation, aim to accurately predict masks with extremely fine details (such as hair). Most existing methods focus on salient, single foreground objects. While…

Multi-exposure image fusion (MEF) is an important area in computer vision and has attracted increasing interests in recent years. Apart from conventional algorithms, deep learning techniques have also been applied to multi-exposure image…

Fine-tuning adapts pretrained networks to new objectives. Whether the resulting depth profile of representational change reflects an intrinsic property of the model or the magnitude of gradient flow has not been tested directly. We measure…

Fourier ptychographic microscopy (FPM) is a recently proposed computational imaging technique with both high resolution and wide field-of-view. In current FP experimental setup, the dark-field images with high-angle illuminations are easily…

Physics Informed Neural Networks (PINNs) often exhibit failure modes in which the PDE residual loss converges while the solution error stays large, a phenomenon traditionally blamed on local optima separated from the true solution by steep…

The multi-frequency temporal phase unwrapping (MF-TPU) method, as a classical phase unwrapping algorithm for fringe projection profilometry (FPP), is capable of eliminating the phase ambiguities even in the presence of surface…

Parameter-efficient fine-tuning (PEFT) allows model builders to capture the task-specific parameters into adapters, which are a fraction of the size of the original base model. Popularity of PEFT technique for fine-tuning has led to the…

Federated learning is a privacy-preserving machine learning technique that learns a shared model across decentralized clients. It can alleviate privacy concerns of personal re-identification, an important computer vision task. In this work,…