Related papers: Model soups need only one ingredient

Continued pretraining offers a promising solution for adapting foundation models to a new target domain. However, in specialized domains, available datasets are often very small, limiting the applicability of SSL methods developed for…

After training complex deep learning models, a common task is to compress the model to reduce compute and storage demands. When compressing, it is desirable to preserve the original model's per-example decisions (e.g., to go beyond top-1…

Monocular 3D object detection (Mono 3Det) aims to identify 3D objects from a single RGB image. However, existing methods often assume training and test data follow the same distribution, which may not hold in real-world test scenarios. To…

Accurately predicting molecular properties is a challenging but essential task in drug discovery. Recently, many mono-modal deep learning methods have been successfully applied to molecular property prediction. However, the inherent…

Few-shot object detection (FSOD) aims at extending a generic detector for novel object detection with only a few training examples. It attracts great concerns recently due to the practical meanings. Meta-learning has been demonstrated to be…

Recent advances in multimodal learning have achieved remarkable success across diverse vision-language tasks. However, such progress heavily relies on large-scale image-text datasets, making training costly and inefficient. Prior efforts in…

The diversity of deep learning applications, datasets, and neural network architectures necessitates a careful selection of the architecture and data that match best to a target application. As an attempt to mitigate this dilemma, this…

The diversity and complementarity of sensors available for Earth Observations (EO) calls for developing bespoke self-supervised multimodal learning approaches. However, current multimodal EO datasets and models typically focus on a single…

We present a learning based approach for multi-view stereopsis (MVS). While current deep MVS methods achieve impressive results, they crucially rely on ground-truth 3D training data, and acquisition of such precise 3D geometry for…

Training a diverse ensemble of models has several practical applications such as providing candidates for model selection with better out-of-distribution (OOD) generalization, and enabling the detection of OOD samples via Bayesian…

The paper presents a strategy to construct an incremental Singular Value Decomposition (SVD) for time-evolving, spatially 3D discrete data sets. A low memory access procedure for reducing and deploying the snapshot data is presented.…

In this work we present a novel methodology that combines Higher Order Singular Value Decomposition (HOSVD) with Deep Learning (DL) techniques for super-resolution in computational fluid dynamics (CFD) and sparse experimental datasets. This…

We investigate whether synthetic images generated by diffusion models can enhance multi-label classification of protein subcellular localization. Specifically, we implement a simplified class-conditional denoising diffusion probabilistic…

The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks. Much research in NLP has focused on efficient methods for storing and adapting different types of knowledge, e.g., in dedicated…

Monocular depth estimation, enabled by self-supervised learning, is a key technique for 3D perception in computer vision. However, it faces significant challenges in real-world scenarios, which encompass adverse weather variations, motion…

Convolutional neural networks (CNNs) have emerged as the state-of-the-art in multiple vision tasks including depth estimation. However, memory and computing power requirements remain as challenges to be tackled in these models. Monocular…

Unsupervised methods have showed promising results on monocular depth estimation. However, the training data must be captured in scenes without moving objects. To push the envelope of accuracy, recent methods tend to increase their model…

We propose a new method named OnePose for object pose estimation. Unlike existing instance-level or category-level methods, OnePose does not rely on CAD models and can handle objects in arbitrary categories without instance- or…

The ability to detect out-of-distribution (OOD) samples is vital to secure the reliability of deep neural networks in real-world applications. Considering the nature of OOD samples, detection methods should not have hyperparameters that…

We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In contrast to conventional box-supervised segmentation, where the…