|
|
Ishaan Gulrajani, Kundan Kumar, Faruk Ahmed, Adrien Ali Taiga, Francesco Visin, David Vazquez, et al. (2017). PixelVAE: A Latent Variable Model for Natural Images. In 5th International Conference on Learning Representations.
Abstract: Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representation and generate samples that preserve global structure but tend to suffer from image blurriness. PixelCNNs model sharp contours and details very well, but lack an explicit latent representation and have difficulty modeling large-scale structure in a computationally efficient way. In this paper, we present PixelVAE, a VAE model with an autoregressive decoder based on PixelCNN. The resulting architecture achieves state-of-the-art log-likelihood on binarized MNIST. We extend PixelVAE to a hierarchy of multiple latent variables at different scales; this hierarchical model achieves competitive likelihood on 64x64 ImageNet and generates high-quality samples on LSUN bedrooms.
Keywords: Deep Learning; Unsupervised Learning
|
|
|
|
Pau Rodriguez, Jordi Gonzalez, Jordi Cucurull, Josep M. Gonfaus, & Xavier Roca. (2017). Regularizing CNNs with Locally Constrained Decorrelations. In 5th International Conference on Learning Representations.
|
|
|
|
Yaxing Wang, Joost Van de Weijer, Lu Yu, & Shangling Jui. (2022). Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data. In 10th International Conference on Learning Representations.
Abstract: Conditional image synthesis is an integral part of many X2I translation systems, including image-to-image, text-to-image and audio-to-image translation systems. Training these large systems generally requires huge amounts of training data.
Therefore, we investigate knowledge distillation to transfer knowledge from a high-quality unconditioned generative model (e.g., StyleGAN) to a conditioned synthetic image generation modules in a variety of systems. To initialize the conditional and reference branch (from a unconditional GAN) we exploit the style mixing characteristics of high-quality GANs to generate an infinite supply of style-mixed triplets to perform the knowledge distillation. Extensive experimental results in a number of image generation tasks (i.e., image-to-image, semantic segmentation-to-image, text-to-image and audio-to-image) demonstrate qualitatively and quantitatively that our method successfully transfers knowledge to the synthetic image generation modules, resulting in more realistic images than previous methods as confirmed by a significant drop in the FID.
|
|
|
|
Simone Zini, Alex Gomez-Villa, Marco Buzzelli, Bartlomiej Twardowski, Andrew D. Bagdanov, & Joost Van de Weijer. (2023). Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training. In 11th International Conference on Learning Representations.
Abstract: Several recent works on self-supervised learning are trained by mapping different augmentations of the same image to the same feature representation. The data augmentations used are of crucial importance to the quality of learned feature representations. In this paper, we analyze how the color jitter traditionally used in data augmentation negatively impacts the quality of the color features in learned feature representations. To address this problem, we propose a more realistic, physics-based color data augmentation – which we call Planckian Jitter – that creates realistic variations in chromaticity and produces a model robust to illumination changes that can be commonly observed in real life, while maintaining the ability to discriminate image content based on color information. Experiments confirm that such a representation is complementary to the representations learned with the currently-used color jitter augmentation and that a simple concatenation leads to significant performance gains on a wide range of downstream datasets. In addition, we present a color sensitivity analysis that documents the impact of different training methods on model neurons and shows that the performance of the learned features is robust with respect to illuminant variations.
|
|
|
|
Sergio Escalera, Alicia Fornes, Oriol Pujol, Alberto Escudero, & Petia Radeva. (2009). Circular Blurred Shape Model for Symbol Spotting in Documents. In 16th IEEE International Conference on Image Processing (pp. 1985–1988).
Abstract: Symbol spotting problem requires feature extraction strategies able to generalize from training samples and to localize the target object while discarding most part of the image. In the case of document analysis, symbol spotting techniques have to deal with a high variability of symbols' appearance. In this paper, we propose the Circular Blurred Shape Model descriptor. Feature extraction is performed capturing the spatial arrangement of significant object characteristics in a correlogram structure. Shape information from objects is shared among correlogram regions, being tolerant to the irregular deformations. Descriptors are learnt using a cascade of classifiers and Abadoost as the base classifier. Finally, symbol spotting is performed by means of a windowing strategy using the learnt cascade over plan and old musical score documents. Spotting and multi-class categorization results show better performance comparing with the state-of-the-art descriptors.
|
|
|
|
Jose Manuel Alvarez, Ferran Diego, Joan Serrat, & Antonio Lopez. (2009). Automatic Ground-truthing using video registration for on-board detection algorithms. In 16th IEEE International Conference on Image Processing (pp. 4389–4392).
Abstract: Ground-truth data is essential for the objective evaluation of object detection methods in computer vision. Many works claim their method is robust but they support it with experiments which are not quantitatively assessed with regard some ground-truth. This is one of the main obstacles to properly evaluate and compare such methods. One of the main reasons is that creating an extensive and representative ground-truth is very time consuming, specially in the case of video sequences, where thousands of frames have to be labelled. Could such a ground-truth be generated, at least in part, automatically? Though it may seem a contradictory question, we show that this is possible for the case of video sequences recorded from a moving camera. The key idea is transferring existing frame segmentations from a reference sequence into another video sequence recorded at a different time on the same track, possibly under a different ambient lighting. We have carried out experiments on several video sequence pairs and quantitatively assessed the precision of the transformed ground-truth, which prove that our approach is not only feasible but also quite accurate.
|
|
|
|
Angel Sappa, & Mohammad Rouhani. (2009). Efficient Distance Estimation for Fitting Implicit Quadric Surfaces. In 16th IEEE International Conference on Image Processing (3521–3524).
Abstract: This paper presents a novel approach for estimating the shortest Euclidean distance from a given point to the corresponding implicit quadric fitting surface. It first estimates the orthogonal orientation to the surface from the given point; then the shortest distance is directly estimated by intersecting the implicit surface with a line passing through the given point according to the estimated orthogonal orientation. The proposed orthogonal distance estimation is easily obtained without increasing computational complexity; hence it can be used in error minimization surface fitting frameworks. Comparisons of the proposed metric with previous approaches are provided to show both improvements in CPU time as well as in the accuracy of the obtained results. Surfaces fitted by using the proposed geometric distance estimation and state of the art metrics are presented to show the viability of the proposed approach.
|
|
|
|
Carlo Gatta, & Petia Radeva. (2009). Bilateral Enhancers. In 16th IEEE International Conference on Image Processing (pp. 3161–3165).
Abstract: Ten years ago the concept of bilateral filtering (BF) became popular in the image processing community. The core of the idea is to blend the effect of a spatial filter, as e.g. the Gaussian filter, with the effect of a filter that acts on image values. The two filters acts on orthogonal domains of a picture: the 2D lattice of the image support and the intensity (or color) domain. The BF approach is an intuitive way to blend these two filters giving rise to algorithms that perform difficult tasks requiring a relatively simple design. In this paper we extend the concept of BF, proposing the bilateral enhancers (BE). We show how to design proper functions to obtain an edge-preserving smoothing and a selective sharpening. Moreover, we show that the proposed algorithm can perform edge-preserving smoothing and selective sharpening simultaneously in a single filtering.
|
|
|
|
Fernando Barrera, Felipe Lumbreras, & Angel Sappa. (2010). Multimodal Template Matching based on Gradient and Mutual Information using Scale-Space. In 17th IEEE International Conference on Image Processing (2749–2752).
Abstract: This paper presents the combined use of gradient and mutual information for infrared and intensity templates matching. We propose to joint: (i) feature matching in a multiresolution context and (ii) information propagation through scale-space representations. Our method consists in combining mutual information with a shape descriptor based on gradient, and propagate them following a coarse-to-fine strategy. The main contributions of this work are: to offer a theoretical formulation towards a multimodal stereo matching; to show that gradient and mutual information can be reinforced while they are propagated between consecutive levels; and to show that they are valid cost functions in multimodal template matchings. Comparisons are presented showing the improvements and viability of the proposed approach.
|
|
|
|
Mohammad Rouhani, & Angel Sappa. (2010). A Fast accurate Implicit Polynomial Fitting Approach. In 17th IEEE International Conference on Image Processing (1429–1432).
Abstract: This paper presents a novel hybrid approach that combines state of the art fitting algorithms: algebraic-based and geometric-based. It consists of two steps; first, the 3L algorithm is used as an initialization and then, the obtained result, is improved through a geometric approach. The adopted geometric approach is based on a distance estimation that avoids costly search for the real orthogonal distance. Experimental results are presented as well as quantitative comparisons.
|
|
|
|
Mohammad Rouhani, & Angel Sappa. (2011). Implicit B-Spline Fitting Using the 3L Algorithm. In 18th IEEE International Conference on Image Processing (pp. 893–896).
|
|
|
|
Ekaterina Zaytseva, & Jordi Vitria. (2012). A search based approach to non maximum suppression in face detection. In 19th IEEE International Conference on Image Processing.
Abstract: Poster
paper TA.P5.12
Face detectors typically produce a large number of false positives and this leads to the need to have a further non maximum suppression stage to eliminate multiple and spurious responses. This stage is based on considering spatial heuristics: true positive responses are selected by implicitly considering several restrictions on the spatial distribution of detector responses in natural images. In this paper we analyze the limitations of this approach and propose an efficient search method to overcome them. Results show how the application of this new non-maximum suppression approach to a simple face detector boosts its performance to state of the art results.
|
|
|
|
Rahat Khan, Joost Van de Weijer, Dimosthenis Karatzas, & Damien Muselet. (2013). Towards multispectral data acquisition with hand-held devices. In 20th IEEE International Conference on Image Processing (pp. 2053–2057).
Abstract: We propose a method to acquire multispectral data with handheld devices with front-mounted RGB cameras. We propose to use the display of the device as an illuminant while the camera captures images illuminated by the red, green and
blue primaries of the display. Three illuminants and three response functions of the camera lead to nine response values which are used for reflectance estimation. Results are promising and show that the accuracy of the spectral reconstruction improves in the range from 30-40% over the spectral
reconstruction based on a single illuminant. Furthermore, we propose to compute sensor-illuminant aware linear basis by discarding the part of the reflectances that falls in the sensorilluminant null-space. We show experimentally that optimizing reflectance estimation on these new basis functions decreases
the RMSE significantly over basis functions that are independent to sensor-illuminant. We conclude that, multispectral data acquisition is potentially possible with consumer hand-held devices such as tablets, mobiles, and laptops, opening up applications which are currently considered to be unrealistic.
Keywords: Multispectral; mobile devices; color measurements
|
|
|
|
Shida Beigpour, Marc Serra, Joost Van de Weijer, Robert Benavente, Maria Vanrell, Olivier Penacchio, et al. (2013). Intrinsic Image Evaluation On Synthetic Complex Scenes. In 20th IEEE International Conference on Image Processing (pp. 285–289).
Abstract: Scene decomposition into its illuminant, shading, and reflectance intrinsic images is an essential step for scene understanding. Collecting intrinsic image groundtruth data is a laborious task. The assumptions on which the ground-truth
procedures are based limit their application to simple scenes with a single object taken in the absence of indirect lighting and interreflections. We investigate synthetic data for intrinsic image research since the extraction of ground truth is straightforward, and it allows for scenes in more realistic situations (e.g, multiple illuminants and interreflections). With this dataset we aim to motivate researchers to further explore intrinsic image decomposition in complex scenes.
|
|
|
|
Michal Drozdzal, Jordi Vitria, Santiago Segui, Carolina Malagelada, Fernando Azpiroz, & Petia Radeva. (2014). Intestinal event segmentation for endoluminal video analysis. In 21st IEEE International Conference on Image Processing (pp. 3592–3596).
|
|
