Related papers: FastFill: Efficient Compatible Model Update

Due to their highly structured characteristics, faces are easier to recover than natural scenes for blind image super-resolution. Therefore, we can extract the degradation representation of an image from the low-quality and recovered face…

We introduce a lightweight and accurate architecture for resource-efficient visual correspondence. Our method, dubbed XFeat (Accelerated Features), revisits fundamental design choices in convolutional neural networks for detecting,…

This paper introduces a new architectural framework, known as input fast-forwarding, that can enhance the performance of deep networks. The main idea is to incorporate a parallel path that sends representations of input values forward to…

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric. Our pipeline's modular structure allows…

While several feature embedding models have been developed in the literature, comparisons of these embeddings have largely focused on their numerical performance in classification-related downstream applications. However, an interpretable…

We introduce \emph{ReMatching}, a novel shape correspondence solution based on the functional maps framework. Our method, by exploiting a new and appropriate \emph{re}-meshing paradigm, can target shape-\emph{matching} tasks even on meshes…

The fashion industry has been identified as a major contributor to waste and emissions, leading to an increased interest in promoting the second-hand market. Machine learning methods play an important role in facilitating the creation and…

Future deep learning models will be distinguished by systems that perpetually learn through interaction, imagination, and cooperation, blurring the line between training and inference. This makes continual learning a critical challenge, as…

Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge…

It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the training bias. Despite the promising performances, super slow…

Heavy computation is a bottleneck limiting deep-learningbased feature matching algorithms to be applied in many realtime applications. However, existing lightweight networks optimized for Euclidean data cannot address classical feature…

Distributed model fitting refers to the process of fitting a mathematical or statistical model to the data using distributed computing resources, such that computing tasks are divided among multiple interconnected computers or nodes, often…

We present Recurrent Fitting (ReFit), a neural network architecture for single-image, parametric 3D human reconstruction. ReFit learns a feedback-update loop that mirrors the strategy of solving an inverse problem through optimization. At…

Counterfactual examples are minimal edits to an input that alter a model's prediction. They are widely employed in explainable AI to probe model behavior and in natural language processing (NLP) to augment training data. However, generating…

Embeddings mapping high-dimensional discrete input to lower-dimensional continuous vector spaces have been widely adopted in machine learning applications as a way to capture domain semantics. Interviewing 13 embedding users across…

Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits,…

Currently used semantic parsing systems deployed in voice assistants can require weeks to train. Datasets for these models often receive small and frequent updates, data patches. Each patch requires training a new model. To reduce training…

Retrieval augmented generation (RAG) pipelines are commonly used in tasks such as question-answering (QA), relying on retrieving relevant documents from a vector store computed using a pretrained embedding model. However, if the retrieved…

E-commerce information retrieval (IR) systems struggle to simultaneously achieve high accuracy in interpreting complex user queries and maintain efficient processing of vast product catalogs. The dual challenge lies in precisely matching…

Autonomous agents interacting with the real world need to learn new concepts efficiently and reliably. This requires learning in a low-data regime, which is a highly challenging problem. We address this task by introducing a fast…