Related papers: Could Giant Pretrained Image Models Extract Univer…

Despite the remarkable success of foundation models, their task-specific fine-tuning paradigm makes them inconsistent with the goal of general perception modeling. The key to eliminating this inconsistency is to use generalist models for…

Model pre-training is a cornerstone of modern visual recognition systems. Although fully supervised pre-training on datasets like ImageNet is still the de-facto standard, recent studies suggest that large-scale weakly supervised…

We introduce a foundation model for event classification in high-energy physics, built on a Graph Neural Network architecture and trained on 120 million simulated proton-proton collision events spanning 12 distinct physics processes. The…

Self-supervised video transformer pre-training has recently benefited from the mask-and-predict pipeline. They have demonstrated outstanding effectiveness on downstream video tasks and superior data efficiency on small datasets. However,…

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

Recent advances in training vision-language models have demonstrated unprecedented robustness and transfer learning effectiveness; however, standard computer vision datasets are image-only, and therefore not well adapted to such training…

Modern deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns, limiting their commercial use. Recent works suggest synthetic data as an alternative,…

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to costly training a large-scale model from scratch, how to…

Foundation models pretrained on large-scale natural images are widely adapted to various cross-domain low-resource downstream tasks, benefiting from generalizable and transferable patterns captured by their representations. However, these…

Large speech models-derived features have recently shown increased performance over signal-based features across multiple downstream tasks, even when the networks are not finetuned towards the target task. In this paper we show the results…

Robot perception systems need to perform reliable image segmentation in real-time on noisy, raw perception data. State-of-the-art segmentation approaches use large CNN models and carefully constructed datasets; however, these models focus…

Current vision language pretraining models are dominated by methods using region visual features extracted from object detectors. Given their good performance, the extract-then-process pipeline significantly restricts the inference speed…

Fine-grained and instance-level recognition methods are commonly trained and evaluated on specific domains, in a model per domain scenario. Such an approach, however, is impractical in real large-scale applications. In this work, we address…

Fine-tuning models that have been pre-trained on large datasets has become a cornerstone of modern machine learning workflows. With the widespread availability of online model repositories, such as Hugging Face, it is now easier than ever…

Foundation models are rapidly transforming Earth Observation data mining by enabling generalizable and scalable solutions for key tasks such as scene classification and semantic segmentation. While most efforts in the geospatial domain have…

Visual servoing enables robots to precisely position their end-effector relative to a target object. While classical methods rely on hand-crafted features and thus are universally applicable without task-specific training, they often…

Over the last years, advancements in deep learning models for computer vision have led to a dramatic improvement in their image classification accuracy. However, models with a higher accuracy in the task they were trained on do not…

The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we…

Facial images disclose many hidden personal traits such as age, gender, race, health, emotion, and psychology. Understanding these traits will help to classify the people in different attributes. In this paper, we have presented a novel…

Foundation models have reshaped the landscape of Remote Sensing (RS) by enhancing various image interpretation tasks. Pretraining is an active research topic, encompassing supervised and self-supervised learning methods to initialize model…