Skip to search formSkip to main contentSkip to account menu

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

The Pyramid Vision Transformer (PVT) is introduced, which overcomes the difficulties of porting Transformer to various dense prediction tasks and is validated through extensive experiments, showing that it boosts the performance of many downstream tasks, including object detection, instance and semantic segmentation.
View on IEEE (opens in a new tab)

PVTv2: Improved Baselines with Pyramid Vision Transformer

This work improves the original Pyramid Vision Transformer (PVT v1) by adding three designs: a linear complexity attention layer, an overlapping patch embedding, and a convolutional feed-forward network to reduce the computational complexity of PVT v1 to linearity and provide significant improvements on fundamental vision tasks.
View PDF on arXiv (opens in a new tab)

Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content

This work proposes a novel visual try-on network, namely Adaptive Content Generating and Preserving Network (ACGPN), which can generate photo-realistic images with much better perceptual quality and richer fine-details.
View on IEEE (opens in a new tab)

TransTrack: Multiple-Object Tracking with Transformer

This work proposes TransTrack, a baseline for MOT with Transformer and introduces a set of learned object queries into the pipeline to enable detecting new-coming objects, and demonstrates a much simple and effective method based on query-key mechanism that could achieve competitive 65.8% MOTA on the MOT17 challenge dataset.
View PDF on arXiv (opens in a new tab)

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

D4LCN overcomes the limitation of conventional 2D convolutions and narrows the gap between image representation and 3D point cloud representation, where the filters and their receptive fields can be automatically learned from image-based depth maps.
View on IEEE (opens in a new tab)

Parser-Free Virtual Try-on via Distilling Appearance Flows

This work proposes a novel approach, "teacher-tutor-student" knowledge distillation, which is able to produce highly photo-realistic images without human parsing, possessing several appealing advantages compared to prior arts.
View on IEEE (opens in a new tab)

Online Knowledge Distillation via Collaborative Learning

This work carefully design multiple methods to generate soft target as supervisions by effectively ensembling predictions of students and distorting the input images to consistently improve the generalization ability of deep neural networks (DNNs) that have different learning capacities.
View on IEEE (opens in a new tab)

DetCo: Unsupervised Contrastive Learning for Object Detection

  • Enze XieJian Ding P. Luo
  • Computer Science
    IEEE International Conference on Computer Vision
  • 9 February 2021
Extensive experiments demonstrate that DetCo not only outperforms recent methods on a series of 2D and 3D instance-level detection tasks, but also competitive on image classification.
View on IEEE (opens in a new tab)

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation

This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images and allows the generator to be fine-tuned on-the-fly in a progressive manner regularized by feature distance obtained by the discriminator in GAN.
View on IEEE (opens in a new tab)

Segmenting Transparent Object in the Wild with Transformer

A novel Transformer-based segmentation pipeline termed Trans2Seg is proposed, which significantly outperforms all the CNN-based methods, showing the proposed algorithm’s potential ability to solve transparent object segmentation.
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)