相关论文: Visual Tuning

The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of pre-trained models for specific tasks. Traditional…

Parameter-Efficient Tuning (PETuning) methods have been deemed by many as the new paradigm for using pretrained language models (PLMs). By tuning just a fraction amount of parameters comparing to full model finetuning, PETuning methods…

In recent years, deep neural networks have known a wide success in various application domains. However, they require important computational and memory resources, which severely hinders their deployment, notably on mobile devices or for…

Image captioning is a research area of immense importance, aiming to generate natural language descriptions for visual content in the form of still images. The advent of deep learning and more recently vision-language pre-training…

Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the…

Pre-training models on Imagenet or other massive datasets of real images has led to major advances in computer vision, albeit accompanied with shortcomings related to curation cost, privacy, usage rights, and ethical issues. In this paper,…

Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from…

Accurate uncertainty estimation is vital to trustworthy machine learning, yet uncertainties typically have to be learned for each task anew. This work introduces the first pretrained uncertainty modules for vision models. Similar to…

Can a small amount of verified goal information steer the expensive self-supervised pretraining of foundation models? Standard pretraining optimizes a fixed proxy objective (e.g., next-token prediction), which can misallocate compute away…

In deep learning, transferring information from a pretrained network to a downstream task by finetuning has many benefits. The choice of task head plays an important role in fine-tuning, as the pretrained and downstream tasks are usually…

The "pre-training then fine-tuning (FT)" paradigm is widely adopted to boost the model performance of deep learning-based methods for medical volumetric segmentation. However, conventional full FT incurs high computational and memory costs.…

How can we train models whose post-trained capabilities survive subsequent fine-tuning? Rather than focusing on downstream interventions to mitigate forgetting of upstream capabilities, we study how upstream training choices - that is, the…

A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a…

Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and object detection. Contemporary techniques can be divided into two…

Vision-Language Pretraining (VLP) models have recently successfully facilitated many cross-modal downstream tasks. Most existing works evaluated their systems by comparing the fine-tuned downstream task performance. However, only average…

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…

How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. delivering a package)? We study this question by integrating a generic perceptual skill set…

Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of full fine-tuning…

This paper presents a novel layered framework that integrates visual foundation models to improve robot manipulation tasks and motion planning. The framework consists of five layers: Perception, Cognition, Planning, Execution, and Learning.…

The intrinsic difficulty in adapting deep learning models to non-stationary environments limits the applicability of neural networks to real-world tasks. This issue is critical in practical supervised learning settings, such as the ones in…