English
Related papers

Related papers: Indices Matter: Learning to Index for Deep Image M…

200 papers

We show that existing upsampling operators can be unified using the notion of the index function. This notion is inspired by an observation in the decoding process of deep image matting where indices-guided unpooling can often recover…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Hao Lu , Yutong Dai , Chunhua Shen , Songcen Xu

To work at scale, a complete image indexing system comprises two components: An inverted file index to restrict the actual search to only a subset that should contain most of the items relevant to the query; An approximate distance…

Computer Vision and Pattern Recognition · Computer Science 2017-12-14 Himalaya Jain , Joaquin Zepeda , Patrick Pérez , Rémi Gribonval

The emergence of learned indexes has caused a paradigm shift in our perception of indexing by considering indexes as predictive models that estimate keys' positions within a data set, resulting in notable improvements in key search…

Databases · Computer Science 2024-08-09 Alireza Heidari , Amirhossein Ahmadi , Wei Zhang

Metric learning networks are used to compute image embeddings, which are widely used in many applications such as image retrieval and face recognition. In this paper, we propose to use network distillation to efficiently compute image…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Lu Yu , Vacit Oguz Yazici , Xialei Liu , Joost van de Weijer , Yongmei Cheng , Arnau Ramisa

We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an…

Computer Vision and Pattern Recognition · Computer Science 2016-11-29 Klaus Greff , Antti Rasmus , Mathias Berglund , Tele Hotloo Hao , Jürgen Schmidhuber , Harri Valpola

We show that learning affinity in upsampling provides an effective and efficient approach to exploit pairwise interactions in deep networks. Second-order features are commonly used in dense prediction to build adjacent relations with a…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Yutong Dai , Hao Lu , Chunhua Shen

In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks. The main innovation of the framework…

Machine Learning · Computer Science 2013-12-23 Yunlong He , Koray Kavukcuoglu , Yun Wang , Arthur Szlam , Yanjun Qi

Driven by Convolutional Neural Networks, object detection and semantic segmentation have gained significant improvements. However, existing methods on the basis of a full top-down module have limited robustness in handling those two tasks…

Computer Vision and Pattern Recognition · Computer Science 2019-03-19 Shihua Huang , Lu Wang

Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Kaifeng Chen , Daniel Salz , Huiwen Chang , Kihyuk Sohn , Dilip Krishnan , Mojtaba Seyedhosseini

Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with…

Computer Vision and Pattern Recognition · Computer Science 2019-09-06 Chaohao Xie , Shaohui Liu , Chao Li , Ming-Ming Cheng , Wangmeng Zuo , Xiao Liu , Shilei Wen , Errui Ding

Recently, much advance has been made in image captioning, and an encoder-decoder framework has achieved outstanding performance for this task. In this paper, we propose an extension of the encoder-decoder framework by adding a component…

Computer Vision and Pattern Recognition · Computer Science 2018-04-04 Wenhao Jiang , Lin Ma , Xinpeng Chen , Hanwang Zhang , Wei Liu

U-Nets have been established as a standard architecture for image-to-image learning problems such as segmentation and inverse problems in imaging. For large-scale data, as it for example appears in 3D medical imaging, the U-Net however has…

Machine Learning · Computer Science 2020-07-01 Christian Etmann , Rihuan Ke , Carola-Bibiane Schönlieb

Variational methods are widely applied to ill-posed inverse problems for they have the ability to embed prior knowledge about the solution. However, the level of performance of these methods significantly depends on a set of parameters,…

Optimization and Control · Mathematics 2020-01-23 Carla Bertocchi , Emilie Chouzenoux , Marie-Caroline Corbineau , Jean-Christophe Pesquet , Marco Prato

We introduce InverseFaceNet, a deep convolutional inverse rendering framework for faces that jointly estimates facial pose, shape, expression, reflectance and illumination from a single input image. By estimating all parameters from just a…

Computer Vision and Pattern Recognition · Computer Science 2018-05-17 Hyeongwoo Kim , Michael Zollhöfer , Ayush Tewari , Justus Thies , Christian Richardt , Christian Theobalt

The goal of image harmonization is adjusting the foreground appearance in a composite image to make the whole image harmonious. To construct paired training images, existing datasets adopt different ways to adjust the illumination…

Computer Vision and Pattern Recognition · Computer Science 2023-08-02 Li Niu , Junyan Cao , Wenyan Cong , Liqing Zhang

Feature representations, both hand-designed and learned ones, are often hard to analyze and interpret, even when they are extracted from visual data. We propose a new approach to study image representations by inverting them with an…

Neural and Evolutionary Computing · Computer Science 2016-04-28 Alexey Dosovitskiy , Thomas Brox

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Ho Man Kwan , Shenghui Song

Training a neural network for a classification task typically assumes that the data to train are given from the beginning. However, in the real world, additional data accumulate gradually and the model requires additional training without…

Machine Learning · Computer Science 2020-04-22 Jangho Kim , Jeesoo Kim , Nojun Kwak

In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining. However, practical deep classifiers often misidentify these samples, leading to erroneous predictions.…

Computer Vision and Pattern Recognition · Computer Science 2023-10-09 Jiawen Xu , Claas Grohnfeldt , Odej Kao

We present a novel and practical deep fully convolutional neural network architecture for semantic pixel-wise segmentation termed SegNet. This core trainable segmentation engine consists of an encoder network, a corresponding decoder…

Computer Vision and Pattern Recognition · Computer Science 2016-10-12 Vijay Badrinarayanan , Alex Kendall , Roberto Cipolla
‹ Prev 1 2 3 10 Next ›