Xinhang Song, Shuqiang Jiang, & Luis Herranz. (2017). Combining Models from Multiple Sources for RGB-D Scene Recognition. In 26th International Joint Conference on Artificial Intelligence (pp. 4523–4529).
Abstract: Depth can complement RGB with useful cues about object volumes and scene layout. However, RGB-D image datasets are still too small for directly training deep convolutional neural networks (CNNs), in contrast to the massive monomodal RGB datasets. Previous works in RGB-D recognition typically combine two separate networks for RGB and depth data, pretrained with a large RGB dataset and then fine tuned to the respective target RGB and depth datasets. These approaches have several limitations: 1) only use low-level filters learned from RGB data, thus not being able to exploit properly depth-specific patterns, and 2) RGB and depth features are only combined at high-levels but rarely at lower-levels. In this paper, we propose a framework that leverages both knowledge acquired from large RGB datasets together with depth-specific cues learned from the limited depth data, obtaining more effective multi-source and multi-modal representations. We propose a multi-modal combination method that selects discriminative combinations of layers from the different source models and target modalities, capturing both high-level properties of the task and intrinsic low-level properties of both modalities.
Keywords: Robotics and Vision; Vision and Perception
|
Xinhang Song, Luis Herranz, & Shuqiang Jiang. (2017). Depth CNNs for RGB-D Scene Recognition: Learning from Scratch Better than Transferring from RGB-CNNs. In 31st AAAI Conference on Artificial Intelligence.
Abstract: Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN models and fine-tuning with the target RGB-D dataset. However, we show that this approach has the limitation of hardly reaching bottom layers, which is key to learn modality-specific features. In contrast, we focus on the bottom layers, and propose an alternative strategy to learn depth features combining local weakly supervised training from patches followed by global fine tuning with images. This strategy is capable of learning very discriminative depth-specific features with limited depth images, without resorting to Places-CNN. In addition we propose a modified CNN architecture to further match the complexity of the model and the amount of data available. For RGB-D scene recognition, depth and RGB features are combined by projecting them in a common space and further leaning a multilayer classifier, which is jointly optimized in an end-to-end network. Our framework achieves state-of-the-art accuracy on NYU2 and SUN RGB-D in both depth only and combined RGB-D data.
Keywords: RGB-D scene recognition; weakly supervised; fine tune; CNN
|
Laura Lopez-Fuentes, Sebastia Massanet, & Manuel Gonzalez-Hidalgo. (2017). Image vignetting reduction via a maximization of fuzzy entropy. In IEEE International Conference on Fuzzy Systems.
Abstract: In many computer vision applications, vignetting is an undesirable effect which must be removed in a pre-processing step. Recently, an algorithm for image vignetting correction has been presented by means of a minimization of log-intensity entropy. This method relies on an increase of the entropy of the image when it is affected with vignetting. In this paper, we propose a novel algorithm to reduce image vignetting via a maximization of the fuzzy entropy of the image. Fuzzy entropy quantifies the fuzziness degree of a fuzzy set and its value is also modified by the presence of vignetting. The experimental results show that this novel algorithm outperforms in most cases the algorithm based on the minimization of log-intensity entropy both from the qualitative and the quantitative point of view.
|
Adrian Galdran, Aitor Alvarez-Gila, Alessandro Bria, Javier Vazquez, & Marcelo Bertalmio. (2018). On the Duality Between Retinex and Image Dehazing. In 31st IEEE Conference on Computer Vision and Pattern Recognition (8212–8221).
Abstract: Image dehazing deals with the removal of undesired loss of visibility in outdoor images due to the presence of fog. Retinex is a color vision model mimicking the ability of the Human Visual System to robustly discount varying illuminations when observing a scene under different spectral lighting conditions. Retinex has been widely explored in the computer vision literature for image enhancement and other related tasks. While these two problems are apparently unrelated, the goal of this work is to show that they can be connected by a simple linear relationship. Specifically, most Retinex-based algorithms have the characteristic feature of always increasing image brightness, which turns them into ideal candidates for effective image dehazing by directly applying Retinex to a hazy image whose intensities have been inverted. In this paper, we give theoretical proof that Retinex on inverted intensities is a solution to the image dehazing problem. Comprehensive qualitative and quantitative results indicate that several classical and modern implementations of Retinex can be transformed into competing image dehazing algorithms performing on pair with more complex fog removal methods, and can overcome some of the main challenges associated with this problem.
Keywords: Image color analysis; Task analysis; Atmospheric modeling; Computer vision; Computational modeling; Lighting
|
|
Abel Gonzalez-Garcia, Joost Van de Weijer, & Yoshua Bengio. (2018). Image-to-image translation for cross-domain disentanglement. In 32nd Annual Conference on Neural Information Processing Systems.
|
Hugo Prol, Vincent Dumoulin, & Luis Herranz. (2018). Cross-Modulation Networks for Few-Shot Learning.
Abstract: A family of recent successful approaches to few-shot learning relies on learning an embedding space in which predictions are made by computing similarities between examples. This corresponds to combining information between support and query examples at a very late stage of the prediction pipeline. Inspired by this observation, we hypothesize that there may be benefits to combining the information at various levels of abstraction along the pipeline. We present an architecture called Cross-Modulation Networks which allows support and query examples to interact throughout the feature extraction process via a feature-wise modulation mechanism. We adapt the Matching Networks architecture to take advantage of these interactions and show encouraging initial results on miniImageNet in the 5-way, 1-shot setting, where we close the gap with state-of-the-art.
|
Luis Herranz, Weiqing Min, & Shuqiang Jiang. (2018). Food recognition and recipe analysis: integrating visual content, context and external knowledge.
Abstract: The central role of food in our individual and social life, combined with recent technological advances, has motivated a growing interest in applications that help to better monitor dietary habits as well as the exploration and retrieval of food-related information. We review how visual content, context and external knowledge can be integrated effectively into food-oriented applications, with special focus on recipe analysis and retrieval, food recommendation and restaurant context as emerging directions.
|
Mikhail Mozerov, Fei Yang, & Joost Van de Weijer. (2019). Sparse Data Interpolation Using the Geodesic Distance Affinity Space. SPL - IEEE Signal Processing Letters, 26(6), 943–947.
Abstract: In this letter, we adapt the geodesic distance-based recursive filter to the sparse data interpolation problem. The proposed technique is general and can be easily applied to any kind of sparse data. We demonstrate its superiority over other interpolation techniques in three experiments for qualitative and quantitative evaluation. In addition, we compare our method with the popular interpolation algorithm presented in the paper on EpicFlow optical flow, which is intuitively motivated by a similar geodesic distance principle. The comparison shows that our algorithm is more accurate and considerably faster than the EpicFlow interpolation technique.
|
Victoria Ruiz, Angel Sanchez, Jose F. Velez, & Bogdan Raducanu. (2019). Automatic Image-Based Waste Classification. In International Work-Conference on the Interplay Between Natural and Artificial Computation. From Bioinspired Systems and Biomedical Applications to Machine Learning (Vol. 11487, 422–431). LNCS.
Abstract: The management of solid waste in large urban environments has become a complex problem due to increasing amount of waste generated every day by citizens and companies. Current Computer Vision and Deep Learning techniques can help in the automatic detection and classification of waste types for further recycling tasks. In this work, we use the TrashNet dataset to train and compare different deep learning architectures for automatic classification of garbage types. In particular, several Convolutional Neural Networks (CNN) architectures were compared: VGG, Inception and ResNet. The best classification results were obtained using a combined Inception-ResNet model that achieved 88.6% of accuracy. These are the best results obtained with the considered dataset.
Keywords: Computer Vision; Deep learning; Convolutional neural networks; Waste classification
|
Corina Krauter, Ursula Reiter, Albrecht Schmidt, Marc Masana, Rudolf Stollberger, Michael Fuchsjager, et al. (2019). Objective extraction of the temporal evolution of the mitral valve vortex ring from 4D flow MRI. In 27th Annual Meeting & Exhibition of the International Society for Magnetic Resonance in Medicine.
Abstract: The mitral valve vortex ring is a promising flow structure for analysis of diastolic function, however, methods for objective extraction of its formation to dissolution are lacking. We present a novel algorithm for objective extraction of the temporal evolution of the mitral valve vortex ring from magnetic resonance 4D flow data and validated the method against visual analysis. The algorithm successfully extracted mitral valve vortex rings during both early- and late-diastolic filling and agreed substantially with visual assessment. Early-diastolic mitral valve vortex ring properties differed between healthy subjects and patients with ischemic heart disease.
|
Fei Yang, Yongmei Cheng, Joost Van de Weijer, & Mikhail Mozerov. (2020). Improved Discrete Optical Flow Estimation With Triple Image Matching Cost. ACCESS - IEEE Access, 8, 17093–17102.
Abstract: Approaches that use more than two consecutive video frames in the optical flow estimation have a long research history. However, almost all such methods utilize extra information for a pre-processing flow prediction or for a post-processing flow correction and filtering. In contrast, this paper differs from previously developed techniques. We propose a new algorithm for the likelihood function calculation (alternatively the matching cost volume) that is used in the maximum a posteriori estimation. We exploit the fact that in general, optical flow is locally constant in the sense of time and the likelihood function depends on both the previous and the future frame. Implementation of our idea increases the robustness of optical flow estimation. As a result, our method outperforms 9% over the DCFlow technique, which we use as prototype for our CNN based computation architecture, on the most challenging MPI-Sintel dataset for the non-occluded mask metric. Furthermore, our approach considerably increases the accuracy of the flow estimation for the matching cost processing, consequently outperforming the original DCFlow algorithm results up to 50% in occluded regions and up to 9% in non-occluded regions on the MPI-Sintel dataset. The experimental section shows that the proposed method achieves state-of-the-arts results especially on the MPI-Sintel dataset.
|
Rada Deeb, Joost Van de Weijer, Damien Muselet, Mathieu Hebert, & Alain Tremeau. (2019). Deep spectral reflectance and illuminant estimation from self-interreflections. JOSA A - Journal of the Optical Society of America A, 31(1), 105–114.
Abstract: In this work, we propose a convolutional neural network based approach to estimate the spectral reflectance of a surface and spectral power distribution of light from a single RGB image of a V-shaped surface. Interreflections happening in a concave surface lead to gradients of RGB values over its area. These gradients carry a lot of information concerning the physical properties of the surface and the illuminant. Our network is trained with only simulated data constructed using a physics-based interreflection model. Coupling interreflection effects with deep learning helps to retrieve the spectral reflectance under an unknown light and to estimate spectral power distribution of this light as well. In addition, it is more robust to the presence of image noise than classical approaches. Our results show that the proposed approach outperforms state-of-the-art learning-based approaches on simulated data. In addition, it gives better results on real data compared to other interreflection-based approaches.
|
Lu Yu. (2019). Semantic Representation: From Color to Deep Embeddings (Joost Van de Weijer, & Yongmei Cheng, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: One of the fundamental problems of computer vision is to represent images with compact semantically relevant embeddings. These embeddings could then be used in a wide variety of applications, such as image retrieval, object detection, and video search. The main objective of this thesis is to study image embeddings from two aspects: color embeddings and deep embeddings.
In the first part of the thesis we start from hand-crafted color embeddings. We propose a method to order the additional color names according to their complementary nature with the basic eleven color names. This allows us to compute color name representations with high discriminative power of arbitrary length. Psychophysical experiments confirm that our proposed method outperforms baseline approaches. Secondly, we learn deep color embeddings from weakly labeled data by adding an attention strategy. The attention branch is able to correctly identify the relevant regions for each class. The advantage of our approach is that it can learn color names for specific domains for which no pixel-wise labels exists.
In the second part of the thesis, we focus on deep embeddings. Firstly, we address the problem of compressing large embedding networks into small networks, while maintaining similar performance. We propose to distillate the metrics from a teacher network to a student network. Two new losses are introduced to model the communication of a deep teacher network to a small student network: one based on an absolute teacher, where the student aims to produce the same embeddings as the teacher, and one based on a relative teacher, where the distances between pairs of data points is communicated from the teacher to the student. In addition, various aspects of distillation have been investigated for embeddings, including hint and attention layers, semi-supervised learning and cross quality distillation. Finally, another aspect of deep metric learning, namely lifelong learning, is studied. We observed some drift occurs during training of new tasks for metric learning. A method to estimate the semantic drift based on the drift which is experienced by data of the current task during its training is introduced. Having this estimation, previous tasks can be compensated for this drift, thereby improving their performance. Furthermore, we show that embedding networks suffer significantly less from catastrophic forgetting compared to classification networks when learning new tasks.
|
Xialei Liu. (2019). Visual recognition in the wild: learning from rankings in small domains and continual learning in new domains (Joost Van de Weijer, & Andrew Bagdanov, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: Deep convolutional neural networks (CNNs) have achieved superior performance in many visual recognition application, such as image classification, detection and segmentation. In this thesis we address two limitations of CNNs. Training deep CNNs requires huge amounts of labeled data, which is expensive and labor intensive to collect. Another limitation is that training CNNs in a continual learning setting is still an open research question. Catastrophic forgetting is very likely when adapting trained models to new environments or new tasks. Therefore, in this thesis, we aim to improve CNNs for applications with limited data and to adapt CNNs continually to new tasks.
Self-supervised learning leverages unlabelled data by introducing an auxiliary task for which data is abundantly available. In the first part of the thesis, we show how rankings can be used as a proxy self-supervised task for regression problems. Then we propose an efficient backpropagation technique for Siamese networks which prevents the redundant computation introduced by the multi-branch network architecture. In addition, we show that measuring network uncertainty on the self-supervised proxy task is a good measure of informativeness of unlabeled data. This can be used to drive an algorithm for active learning. We then apply our framework on two regression problems: Image Quality Assessment (IQA) and Crowd Counting. For both, we show how to automatically generate ranked image sets from unlabeled data. Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results. We further show that active learning using rankings can reduce labeling effort by up to 50\% for both IQA and crowd counting.
In the second part of the thesis, we propose two approaches to avoiding catastrophic forgetting in sequential task learning scenarios. The first approach is derived from Elastic Weight Consolidation, which uses a diagonal Fisher Information Matrix (FIM) to measure the importance of the parameters of the network. However the diagonal assumption is unrealistic. Therefore, we approximately diagonalize the FIM using a set of factorized rotation parameters. This leads to significantly better performance on continual learning of sequential tasks. For the second approach, we show that forgetting manifests differently at different layers in the network and propose a hybrid approach where distillation is used in the feature extractor and replay in the classifier via feature generation. Our method addresses the limitations of generative image replay and probability distillation (i.e. learning without forgetting) and can naturally aggregate new tasks in a single, well-calibrated classifier. Experiments confirm that our proposed approach outperforms the baselines and some start-of-the-art methods.
|
Carola Figueroa Flores. (2021). Visual Saliency for Object Recognition, and Object Recognition for Visual Saliency (Joost Van de Weijer, & Bogdan Raducanu, Eds.). Ph.D. thesis, Ediciones Graficas Rey, .
Abstract: For humans, the recognition of objects is an almost instantaneous, precise and
extremely adaptable process. Furthermore, we have the innate capability to learn
new object classes from only few examples. The human brain lowers the complexity
of the incoming data by filtering out part of the information and only processing
those things that capture our attention. This, mixed with our biological predisposition to respond to certain shapes or colors, allows us to recognize in a simple
glance the most important or salient regions from an image. This mechanism can
be observed by analyzing on which parts of images subjects place attention; where
they fix their eyes when an image is shown to them. The most accurate way to
record this behavior is to track eye movements while displaying images.
Computational saliency estimation aims to identify to what extent regions or
objects stand out with respect to their surroundings to human observers. Saliency
maps can be used in a wide range of applications including object detection, image
and video compression, and visual tracking. The majority of research in the field has
focused on automatically estimating saliency maps given an input image. Instead, in
this thesis, we set out to incorporate saliency maps in an object recognition pipeline:
we want to investigate whether saliency maps can improve object recognition
results.
In this thesis, we identify several problems related to visual saliency estimation.
First, to what extent the estimation of saliency can be exploited to improve the
training of an object recognition model when scarce training data is available. To
solve this problem, we design an image classification network that incorporates
saliency information as input. This network processes the saliency map through a
dedicated network branch and uses the resulting characteristics to modulate the
standard bottom-up visual characteristics of the original image input. We will refer to this technique as saliency-modulated image classification (SMIC). In extensive
experiments on standard benchmark datasets for fine-grained object recognition,
we show that our proposed architecture can significantly improve performance,
especially on dataset with scarce training data.
Next, we address the main drawback of the above pipeline: SMIC requires an
explicit saliency algorithm that must be trained on a saliency dataset. To solve this,
we implement a hallucination mechanism that allows us to incorporate the saliency
estimation branch in an end-to-end trained neural network architecture that only
needs the RGB image as an input. A side-effect of this architecture is the estimation
of saliency maps. In experiments, we show that this architecture can obtain similar
results on object recognition as SMIC but without the requirement of ground truth
saliency maps to train the system.
Finally, we evaluated the accuracy of the saliency maps that occur as a sideeffect of object recognition. For this purpose, we use a set of benchmark datasets
for saliency evaluation based on eye-tracking experiments. Surprisingly, the estimated saliency maps are very similar to the maps that are computed from human
eye-tracking experiments. Our results show that these saliency maps can obtain
competitive results on benchmark saliency maps. On one synthetic saliency dataset
this method even obtains the state-of-the-art without the need of ever having seen
an actual saliency image for training.
Keywords: computer vision; visual saliency; fine-grained object recognition; convolutional neural networks; images classification
|
