Related papers: Parameter-Efficient Fine-Tuning in Spectral Domain…
Parameter-efficient fine-tuning (PEFT) aims to adapt pre-trained vision models to downstream tasks. Among PEFT paradigms, sparse tuning achieves remarkable performance by adjusting only the weights most relevant to downstream tasks, rather…
Previous studies have demonstrated the effectiveness of point-based neural models on the point cloud analysis task. However, there remains a crucial issue on producing the efficient input embedding for raw point coordinates. Moreover,…
Training large foundation models from scratch for domain-specific applications is almost impossible due to data limits and long-tailed distributions -- taking remote sensing (RS) as an example. Fine-tuning natural image pre-trained models…
Adapting deep learning models to new domains often requires computationally intensive retraining and risks catastrophic forgetting. While fine-tuning enables domain-specific adaptation, it can reduce robustness to distribution shifts,…
Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence. However, the wide range of tasks and high computational costs make full fine-tuning impractical. To overcome this,…
Point cloud compression (PCC) is a key enabler for various 3-D applications, owing to the universality of the point cloud format. Ideally, 3D point clouds endeavor to depict object/scene surfaces that are continuous. Practically, as a set…
Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors. Although coarse-to-fine matching approaches are prevalent, the coarse matching of existing methods is typically…
Parameter-efficient fine-tuning (PEFT) methods such as \lora{} adapt large pretrained models by adding small weight-space updates. While effective, weight deltas are hard to interpret mechanistically, and they do not directly expose…
We present a new method LiST is short for Lite Prompted Self-Training for parameter-efficient fine-tuning of large pre-trained language models (PLMs) for few-shot learning. LiST improves over recent methods that adopt prompt-based…
Achieving a universally high accuracy in object detection is quite challenging, and the mainstream focus in the industry currently lies on detecting specific classes of objects. However, deploying one or multiple object detection networks…
LiDAR-generated point clouds are crucial for perceiving outdoor environments. The segmentation of point clouds is also essential for many applications. Previous research has focused on using self-attention and convolution (local attention)…
There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a…
In this case study, we present a data-efficient point cloud segmentation pipeline and training framework for robust segmentation of unimproved roads and seven other classes. Our method employs a two-stage training framework: first, a…
Efficient analysis of point clouds holds paramount significance in real-world 3D applications. Currently, prevailing point-based models adhere to the PointNet++ methodology, which involves embedding and abstracting point features within a…
Parameter-efficient tunings (PETs) have demonstrated impressive performance and promising perspectives in training large models, while they are still confronted with a common problem: the trade-off between learning new content and…
In contemporary deep learning, a prevalent and effective workflow for solving low-data problems is adapting powerful pre-trained foundation models (FMs) to new tasks via parameter-efficient fine-tuning (PEFT). However, while empirically…
Recommender systems are often asked to serve multiple recommendation scenarios or domains. Fine-tuning a pre-trained CTR model from source domains and adapting it to a target domain allows knowledge transferring. However, optimizing all the…
In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging, due to adopting parameter inefficient global update and…
We present CpT: Convolutional point Transformer - a novel deep learning architecture for dealing with the unstructured nature of 3D point cloud data. CpT is an improvement over existing attention-based Convolutions Neural Networks as well…
Foundation models have achieved great success across diverse domains, including remote sensing (RS), thanks to their versatility and strong generalization abilities. However, most RS foundation models are designed for multispectral data,…