Open AccessPosted Content
Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features
Reads0
Chats0
TLDR
Hyperpixel Flow as mentioned in this paper represents images by "hyperpixels" that leverage a small number of relevant features selected among early to late layers of a convolutional neural network, taking advantage of the condensed features of hyperpixels.Abstract:
Establishing visual correspondences under large intra-class variations requires analyzing images at different levels, from features linked to semantics and context to local patterns, while being invariant to instance-specific details. To tackle these challenges, we represent images by "hyperpixels" that leverage a small number of relevant features selected among early to late layers of a convolutional neural network. Taking advantage of the condensed features of hyperpixels, we develop an effective real-time matching algorithm based on Hough geometric voting. The proposed method, hyperpixel flow, sets a new state of the art on three standard benchmarks as well as a new dataset, SPair-71k, which contains a significantly larger number of image pairs than existing datasets, with more accurate and richer annotations for in-depth analysis.read more
Citations
More filters
Book ChapterDOI
MotionSqueeze: Neural Motion Feature Learning for Video Understanding
TL;DR: This work proposes a trainable neural module, dubbed MotionSqueeze, for effective motion feature extraction, and demonstrates that the proposed method provides a significant gain on four standard benchmarks for action recognition with only a small amount of additional cost, outperforming the state of the art on Something-Something-V1&V2 datasets.
Proceedings ArticleDOI
Semantic Correspondence as an Optimal Transport Problem
TL;DR: This work solves the problem of establishing dense correspondences across semantically similar images by converting the maximization problem to the optimal transport formulation and incorporating the staircase weights into optimal transport algorithm to act as empirical distributions.
Proceedings ArticleDOI
Correspondence Networks With Adaptive Neighbourhood Consensus
TL;DR: This paper proposes a convolutional neural network architecture, called adaptive neighbourhood consensus network (ANC-Net), that can be trained end-to-end with sparse key-point annotations, to handle the task of establishing dense visual correspondences between images containing objects of the same category.
Posted Content
SPair-71k: A Large-scale Benchmark for Semantic Correspondence
TL;DR: A new large-scale benchmark dataset of semantically paired images, SPair-71k, which contains 70,958 image pairs with diverse variations in viewpoint and scale is presented, which is significantly larger in number and contains more accurate and richer annotations.
Book ChapterDOI
Deep Hough-Transform Line Priors
TL;DR: This work reduces the dependency on labeled data by building on the classic knowledge-based priors while using deep networks to learn features, and shows that adding prior knowledge improves data efficiency as line priors no longer need to be learned from data.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.