相关论文: Align then Adapt: Rethinking Parameter-Efficient T…

A promising direction for pre-training 3D point clouds is to leverage the massive amount of data in 2D, whereas the domain gap between 2D and 3D creates a fundamental challenge. This paper proposes a novel approach to point-cloud…

Recently, fine-tuning language models pre-trained on large text corpora have provided huge improvements on vision-and-language (V&L) tasks as well as on pure language tasks. However, fine-tuning the entire parameter set of pre-trained…

Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-scale visual-language…

In this paper, we introduce Attention Prompt Tuning (APT) - a computationally efficient variant of prompt tuning for video-based applications such as action recognition. Prompt tuning approaches involve injecting a set of learnable prompts…

Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast…

Deep motion forecasting models have achieved great success when trained on a massive amount of data. Yet, they often perform poorly when training data is limited. To address this challenge, we propose a transfer learning approach for…

Although action recognition systems can achieve top performance when evaluated on in-distribution test points, they are vulnerable to unanticipated distribution shifts in test data. However, test-time adaptation of video action recognition…

Test-time adaptation (TTA) has emerged as a promising paradigm to handle the domain shifts at test time for medical images from different institutions without using extra training data. However, existing TTA solutions for segmentation tasks…

Though deep learning methods have shown great success in 3D point cloud part segmentation, they generally rely on a large volume of labeled training data, which makes the model suffer from unsatisfied generalization abilities to unseen…

The emerging field semantic communication is driving the research of end-to-end data transmission. By utilizing the powerful representation ability of deep learning models, learned data transmission schemes have exhibited superior…

We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and 3D data for weakly supervised point cloud segmentation. Research studies have shown that 2D and 3D features are complementary for point cloud segmentation.…

Recently Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms, however, these methods often overlook latent information in less prominent regions, leading to increased sensitivity to…

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…

Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization. With a growing number of tasks and limited…

Pretraining Vision Transformers (ViTs) has achieved great success in visual recognition. A following scenario is to adapt a ViT to various image and video recognition tasks. The adaptation is challenging because of heavy computation and…

3D scene understanding from point clouds plays a vital role for various robotic applications. Unfortunately, current state-of-the-art methods use separate neural networks for different tasks like object detection or room layout estimation.…

Parameter-efficient fine-tuning approaches have recently garnered a lot of attention. Having considerably lower number of trainable weights, these methods can bring about scalability and computational effectiveness. In this paper, we look…

The significant effort required to annotate data for new training datasets hinders computer vision research and machine learning in the construction industry. This work explores adapting standard datasets and the latest transformer model…

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…

Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimodal features in…