Search Results - "2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"

Bottleneck Transformers for Visual Recognition by Srinivas, Aravind, Lin, Tsung-Yi, Parmar, Niki, Shlens, Jonathon, Abbeel, Pieter, Vaswani, Ashish

“…We present BoTNet, a conceptually simple yet powerful backbone architecture that incorporates self-attention for multiple computer vision tasks including image…”
Get full text

Dense Contrastive Learning for Self-Supervised Visual Pre-Training by Wang, Xinlong, Zhang, Rufeng, Shen, Chunhua, Kong, Tao, Li, Lei

“…To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for…”
Get full text

Transformer Tracking by Chen, Xin, Yan, Bin, Zhu, Jiawen, Wang, Dong, Yang, Xiaoyun, Lu, Huchuan

“…Correlation acts as a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion…”
Get full text

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers by Zheng, Sixiao, Lu, Jiachen, Zhao, Hengshuang, Zhu, Xiatian, Luo, Zekun, Wang, Yabiao, Fu, Yanwei, Feng, Jianfeng, Xiang, Tao, Torr, Philip H.S., Zhang, Li

“…Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the…”
Get full text

Exploring Simple Siamese Representation Learning by Chen, Xinlei, He, Kaiming

“…Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity…”
Get full text

Coordinate Attention for Efficient Mobile Network Design by Hou, Qibin, Zhou, Daquan, Feng, Jiashi

“…Recent studies on mobile network design have demonstrated the remarkable effectiveness of channel attention (e.g., the Squeeze-and-Excitation attention) for…”
Get full text

Learning to Fuse Asymmetric Feature Maps in Siamese Trackers by Han, Wencheng, Dong, Xingping, Khan, Fahad Shahbaz, Shao, Ling, Shen, Jianbing

“…Recently, Siamese-based trackers have achieved promising performance in visual tracking. Most recent Siamese-based trackers typically employ a depth-wise…”
Get full text

Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning by Li, Bin, Li, Yin, Eliceiri, Kevin W.

“…We address the challenging problem of whole slide image (WSI) classification. WSIs have very high resolutions and usually lack localized annotations. WSI…”
Get full text

DG-Font: Deformable Generative Networks for Unsupervised Font Generation by Xie, Yangchen, Chen, Xinyuan, Sun, Li, Lu, Yue

“…Font generation is a challenging problem especially for some writing systems that consist of a large number of characters and has attracted a lot of attention…”
Get full text

Natural Adversarial Examples by Hendrycks, Dan, Zhao, Kevin, Basart, Steven, Steinhardt, Jacob, Song, Dawn

“…We introduce two challenging datasets that reliably cause machine learning model performance to substantially degrade. The datasets are collected with a simple…”
Get full text

D-NeRF: Neural Radiance Fields for Dynamic Scenes by Pumarola, Albert, Corona, Enric, Pons-Moll, Gerard, Moreno-Noguer, Francesc

“…Neural rendering techniques combining machine learning with geometric reasoning have arisen as one of the most promising approaches for synthesizing novel…”
Get full text

NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections by Martin-Brualla, Ricardo, Radwan, Noha, Sajjadi, Mehdi S. M., Barron, Jonathan T., Dosovitskiy, Alexey, Duckworth, Daniel

“…We present a learning-based method for synthesizing novel views of complex scenes using only unstructured collections of in-the-wild photographs. We build on…”
Get full text

Pre-Trained Image Processing Transformer by Chen, Hanting, Wang, Yunhe, Guo, Tianyu, Xu, Chang, Deng, Yiping, Liu, Zhenhua, Ma, Siwei, Xu, Chunjing, Xu, Chao, Gao, Wen

“…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…”
Get full text

Multi-Stage Progressive Image Restoration by Zamir, Syed Waqas, Arora, Aditya, Khan, Salman, Hayat, Munawar, Khan, Fahad Shahbaz, Yang, Ming-Hsuan, Shao, Ling

“…Image restoration tasks demand a complex balance between spatial details and high-level contextualized information while recovering images. In this paper, we…”
Get full text

Taming Transformers for High-Resolution Image Synthesis by Esser, Patrick, Rombach, Robin, Ommer, Bjorn

“…Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to…”
Get full text

LoFTR: Detector-Free Local Feature Matching with Transformers by Sun, Jiaming, Shen, Zehong, Wang, Yuang, Bao, Hujun, Zhou, Xiaowei

“…We present a novel method for local image feature matching. Instead of performing image feature detection, description, and matching sequentially, we propose…”
Get full text

Image Super-Resolution with Non-Local Sparse Attention by Mei, Yiqun, Fan, Yuchen, Zhou, Yuqian

“…Both Non-Local (NL) operation and sparse representation are crucial for Single Image Super-Resolution (SISR). In this paper, we investigate their combinations…”
Get full text

Scaled-YOLOv4: Scaling Cross Stage Partial Network by Wang, Chien-Yao, Bochkovskiy, Alexey, Liao, Hong-Yuan Mark

“…We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while…”
Get full text

IBRNet: Learning Multi-View Image-Based Rendering by Wang, Qianqian, Wang, Zhicheng, Genova, Kyle, Srinivasan, Pratul, Zhou, Howard, Barron, Jonathan T., Martin-Brualla, Ricardo, Snavely, Noah, Funkhouser, Thomas

“…We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network…”
Get full text

AdaBins: Depth Estimation Using Adaptive Bins by Farooq Bhat, Shariq, Alhashim, Ibraheem, Wonka, Peter

“…We address the problem of estimating a high quality dense depth map from a single RGB input image. We start out with a baseline encoder-decoder convolutional…”
Get full text