Related papers: DropPos: Pre-Training Vision Transformers by Recon…
In this paper, we focus on analyzing and improving the dropout technique for self-attention layers of Vision Transformer, which is important while surprisingly ignored by prior works. In particular, we conduct researches on three core…
High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT), cannot effectively leverage larger images without…
In this paper, we tackle the copy-paste image-to-image composition problem with a focus on object placement learning. Prior methods have leveraged generative models to reduce the reliance for dense supervision. However, this often limits…
Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the…
High annotation costs and limited labels for dense 3D medical imaging tasks have recently motivated an assortment of 3D self-supervised pretraining methods that improve transfer learning performance. However, these methods commonly lack…
Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…
Vision Transformers (ViTs) have been widely used in large-scale Vision and Language Pre-training (VLP) models. Though previous VLP works have proved the effectiveness of ViTs, they still suffer from computational efficiency brought by the…
Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual recognition tasks. However, little effort has been made to reveal the potential of such simple…
Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the…
Recent work on Vision Transformers (VTs) showed that introducing a local inductive bias in the VT architecture helps reducing the number of samples necessary for training. However, the architecture modifications lead to a loss of generality…
Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from…
Dynamic scene reconstruction from casual videos has seen recent remarkable progress. Numerous approaches have attempted to overcome the ill-posedness of the task by distilling priors from 2D foundational models and by imposing hand-crafted…
In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and…
Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features. This is typically done through image retrieval, where the query is matched to the most similar images from a…
Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models. Although previous VLP research has demonstrated the efficacy of ViTs, these efforts still struggle with computational…
Recurrent models have been dominating the field of neural machine translation (NMT) for the past few years. Transformers \citep{vaswani2017attention}, have radically changed it by proposing a novel architecture that relies on a feed-forward…
Modern computer vision is converging on a closed loop in which perception, reasoning and generation mutually reinforce each other. However, this loop remains incomplete: the top-down influence of high-level reasoning on the foundational…
Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the…
Unsupervised learning of vision transformers seeks to pretrain an encoder via pretext tasks without labels. Among them is the Masked Image Modeling (MIM) aligned with pretraining of language transformers by predicting masked patches as a…
Vision Transformers (ViTs) have gained significant popularity in recent years and have proliferated into many applications. However, their behavior under different learning paradigms is not well explored. We compare ViTs trained through…