Related papers: Parallel Pre-trained Transformers (PPT) for Synthe…

The objective of this work is to explore how to effectively and efficiently adapt pre-trained visual foundation models to various downstream tasks of semantic segmentation. Previous methods usually fine-tuned the entire networks for each…

The rapid advancement of deep learning models often attributes to their ability to leverage massive training data. In contrast, such privilege has not yet fully benefited 3D deep learning, mainly due to the limited availability of…

Recently proposed neural network architectures like PointNet [QSMG16] and PointNet++ [QYSG17] have made it possible to apply Deep Learning to 3D point sets. The feature representations of shapes learned by these two networks enabled…

Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision…

As the computing power of modern hardware is increasing strongly, pre-trained deep learning models (e.g., BERT, GPT-3) learned on large-scale datasets have shown their effectiveness over conventional methods. The big progress is mainly…

We present a framework for end-to-end joint quantization of Vision Transformers trained on ImageNet for the purpose of image classification. Unlike prior post-training or block-wise reconstruction methods, we jointly optimize over the…

Fine-grained visual recognition is to classify objects with visually similar appearances into subcategories, which has made great progress with the development of deep CNNs. However, handling subtle differences between different…

Human pose estimation has seen widespread use of transformer models in recent years. Pose transformers benefit from the self-attention map, which captures the correlation between human joint tokens and the image. However, training such…

Physics-Informed Neural Networks (PINNs) have gained popularity in solving nonlinear partial differential equations (PDEs) via integrating physical laws into the training of neural networks, making them superior in many scientific and…

Instance segmentation is applied widely in image editing, image analysis and autonomous driving, etc. However, insufficient data is a common problem in practical applications. The Visual Inductive Priors(VIPriors) Instance Segmentation…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

We propose a fully-convolutional conditional generative model, the latent transformation neural network (LTNN), capable of view synthesis using a light-weight neural network suited for real-time applications. In contrast to existing…

This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image…

Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may…

The ascension of Unmanned Aerial Vehicles (UAVs) in various fields necessitates effective UAV image segmentation, which faces challenges due to the dynamic perspectives of UAV-captured images. Traditional segmentation algorithms falter as…

Action recognition models have achieved impressive results by incorporating scene-level annotations, such as objects, their relations, 3D structure, and more. However, obtaining annotations of scene structure for videos requires a…

Instance segmentation is a fundamental task in computer vision with broad applications across various industries. In recent years, with the proliferation of deep learning and artificial intelligence applications, how to train effective…

Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their…

In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper, we propose a novel multi-task deep network to learn…

Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these methodologies. This…