|
Lu Yu, Vacit Oguz Yazici, Xialei Liu, Joost Van de Weijer, Yongmei Cheng, & Arnau Ramisa. (2019). Learning Metrics from Teachers: Compact Networks for Image Embedding. In 32nd IEEE Conference on Computer Vision and Pattern Recognition (pp. 2907–2916).
Abstract: 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 embeddings with small networks. Network distillation has been successfully applied to improve image classification, but has hardly been explored for metric learning. To do so, we propose two new loss functions that model the
communication of a deep teacher network to a small student network. We evaluate our system in several datasets, including CUB-200-2011, Cars-196, Stanford Online Products and show that embeddings computed using small student networks perform significantly better than those computed using standard networks of similar size. Results on a very compact network (MobileNet-0.25), which can be
used on mobile devices, show that the proposed method can greatly improve Recall@1 results from 27.5% to 44.6%. Furthermore, we investigate various aspects of distillation for embeddings, including hint and attention layers, semisupervised learning and cross quality distillation.
|
|
|
A. Martinez, & Jordi Vitria. (2000). Learning mixture models using a genetic version of the EM algorithm. PRL - Pattern Recognition Letters, 21(8), 759–769.
|
|
|
A. Martinez, & Jordi Vitria. (1998). Learning mixture models with the EM algorithm and genetic algorithms.
|
|
|
Lorenzo Porzi, Markus Hofinger, Idoia Ruiz, Joan Serrat, Samuel Rota Bulo, & Peter Kontschieder. (2020). Learning Multi-Object Tracking and Segmentation from Automatic Annotations. In 33rd IEEE Conference on Computer Vision and Pattern Recognition (pp. 6845–6854).
Abstract: In this work we contribute a novel pipeline to automatically generate training data, and to improve over state-of-the-art multi-object tracking and segmentation (MOTS) methods. Our proposed track mining algorithm turns raw street-level videos into high-fidelity MOTS training data, is scalable and overcomes the need of expensive and time-consuming manual annotation approaches. We leverage state-of-the-art instance segmentation results in combination with optical flow predictions, also trained on automatically harvested training data. Our second major contribution is MOTSNet – a deep learning, tracking-by-detection architecture for MOTS – deploying a novel mask-pooling layer for improved object association over time. Training MOTSNet with our automatically extracted data leads to significantly improved sMOTSA scores on the novel KITTI MOTS dataset (+1.9%/+7.5% on cars/pedestrians), and MOTSNet improves by +4.1% over previously best methods on the MOTSChallenge dataset. Our most impressive finding is that we can improve over previous best-performing works, even in complete absence of manually annotated MOTS training data.
|
|
|
Javier Rodenas, Bhalaji Nagarajan, Marc Bolaños, & Petia Radeva. (2022). Learning Multi-Subset of Classes for Fine-Grained Food Recognition. In 7th International Workshop on Multimedia Assisted Dietary Management (17–26).
Abstract: Food image recognition is a complex computer vision task, because of the large number of fine-grained food classes. Fine-grained recognition tasks focus on learning subtle discriminative details to distinguish similar classes. In this paper, we introduce a new method to improve the classification of classes that are more difficult to discriminate based on Multi-Subsets learning. Using a pre-trained network, we organize classes in multiple subsets using a clustering technique. Later, we embed these subsets in a multi-head model structure. This structure has three distinguishable parts. First, we use several shared blocks to learn the generalized representation of the data. Second, we use multiple specialized blocks focusing on specific subsets that are difficult to distinguish. Lastly, we use a fully connected layer to weight the different subsets in an end-to-end manner by combining the neuron outputs. We validated our proposed method using two recent state-of-the-art vision transformers on three public food recognition datasets. Our method was successful in learning the confused classes better and we outperformed the state-of-the-art on the three datasets.
|
|
|
Ernest Valveny, & Enric Marti. (2001). Learning of structural descriptions of graphic symbols using deformable template matching. In Proc. Sixth Int Document Analysis and Recognition Conf (pp. 455–459).
Abstract: Accurate symbol recognition in graphic documents needs an accurate representation of the symbols to be recognized. If structural approaches are used for recognition, symbols have to be described in terms of their shape, using structural relationships among extracted features. Unlike statistical pattern recognition, in structural methods, symbols are usually manually defined from expertise knowledge, and not automatically infered from sample images. In this work we explain one approach to learn from examples a representative structural description of a symbol, thus providing better information about shape variability. The description of a symbol is based on a probabilistic model. It consists of a set of lines described by the mean and the variance of line parameters, respectively providing information about the model of the symbol, and its shape variability. The representation of each image in the sample set as a set of lines is achieved using deformable template matching.
|
|
|
Jose Manuel Alvarez, Theo Gevers, & Antonio Lopez. (2010). Learning photometric invariance for object detection. IJCV - International Journal of Computer Vision, 90(1), 45–61.
Abstract: Impact factor: 3.508 (the last available from JCR2009SCI). Position 4/103 in the category Computer Science, Artificial Intelligence. Quartile
Color is a powerful visual cue in many computer vision applications such as image segmentation and object recognition. However, most of the existing color models depend on the imaging conditions that negatively affect the performance of the task at hand. Often, a reflection model (e.g., Lambertian or dichromatic reflectance) is used to derive color invariant models. However, this approach may be too restricted to model real-world scenes in which different reflectance mechanisms can hold simultaneously.
Therefore, in this paper, we aim to derive color invariance by learning from color models to obtain diversified color invariant ensembles. First, a photometrical orthogonal and non-redundant color model set is computed composed of both color variants and invariants. Then, the proposed method combines these color models to arrive at a diversified color ensemble yielding a proper balance between invariance (repeatability) and discriminative power (distinctiveness). To achieve this, our fusion method uses a multi-view approach to minimize the estimation error. In this way, the proposed method is robust to data uncertainty and produces properly diversified color invariant ensembles. Further, the proposed method is extended to deal with temporal data by predicting the evolution of observations over time.
Experiments are conducted on three different image datasets to validate the proposed method. Both the theoretical and experimental results show that the method is robust against severe variations in imaging conditions. The method is not restricted to a certain reflection model or parameter tuning, and outperforms state-of-the-art detection techniques in the field of object, skin and road recognition. Considering sequential data, the proposed method (extended to deal with future observations) outperforms the other methods
Keywords: road detection
|
|
|
Jose Manuel Alvarez, Theo Gevers, & Antonio Lopez. (2009). Learning Photometric Invariance from Diversified Color Model Ensembles. In 22nd IEEE Conference on Computer Vision and Pattern Recognition (565–572).
Abstract: Color is a powerful visual cue for many computer vision applications such as image segmentation and object recognition. However, most of the existing color models depend on the imaging conditions affecting negatively the performance of the task at hand. Often, a reflection model (e.g., Lambertian or dichromatic reflectance) is used to derive color invariant models. However, those reflection models might be too restricted to model real-world scenes in which different reflectance mechanisms may hold simultaneously. Therefore, in this paper, we aim to derive color invariance by learning from color models to obtain diversified color invariant ensembles. First, a photometrical orthogonal and non-redundant color model set is taken on input composed of both color variants and invariants. Then, the proposed method combines and weights these color models to arrive at a diversified color ensemble yielding a proper balance between invariance (repeatability) and discriminative power (distinctiveness). To achieve this, the fusion method uses a multi-view approach to minimize the estimation error. In this way, the method is robust to data uncertainty and produces properly diversified color invariant ensembles. Experiments are conducted on three different image datasets to validate the method. From the theoretical and experimental results, it is concluded that the method is robust against severe variations in imaging conditions. The method is not restricted to a certain reflection model or parameter tuning. Further, the method outperforms state-of- the-art detection techniques in the field of object, skin and road recognition.
Keywords: road detection
|
|
|
I. Sorodoc, S. Pezzelle, A. Herbelot, Mariella Dimiccoli, & R. Bernardi. (2018). Learning quantification from images: A structured neural architecture. NLE - Natural Language Engineering, 24(3), 363–392.
Abstract: Major advances have recently been made in merging language and vision representations. Most tasks considered so far have confined themselves to the processing of objects and lexicalised relations amongst objects (content words). We know, however, that humans (even pre-school children) can abstract over raw multimodal data to perform certain types of higher level reasoning, expressed in natural language by function words. A case in point is given by their ability to learn quantifiers, i.e. expressions like few, some and all. From formal semantics and cognitive linguistics, we know that quantifiers are relations over sets which, as a simplification, we can see as proportions. For instance, in most fish are red, most encodes the proportion of fish which are red fish. In this paper, we study how well current neural network strategies model such relations. We propose a task where, given an image and a query expressed by an object–property pair, the system must return a quantifier expressing which proportions of the queried object have the queried property. Our contributions are twofold. First, we show that the best performance on this task involves coupling state-of-the-art attention mechanisms with a network architecture mirroring the logical structure assigned to quantifiers by classic linguistic formalisation. Second, we introduce a new balanced dataset of image scenarios associated with quantification queries, which we hope will foster further research in this area.
|
|
|
Lei Kang, Lichao Zhang, & Dazhi Jiang. (2023). Learning Robust Self-Attention Features for Speech Emotion Recognition with Label-Adaptive Mixup. In IEEE International Conference on Acoustics, Speech and Signal Processing.
Abstract: Speech Emotion Recognition (SER) is to recognize human emotions in a natural verbal interaction scenario with machines, which is considered as a challenging problem due to the ambiguous human emotions. Despite the recent progress in SER, state-of-the-art models struggle to achieve a satisfactory performance. We propose a self-attention based method with combined use of label-adaptive mixup and center loss. By adapting label probabilities in mixup and fitting center loss to the mixup training scheme, our proposed method achieves a superior performance to the state-of-the-art methods.
|
|
|
Hana Jarraya, Oriol Ramos Terrades, & Josep Llados. (2017). Learning structural loss parameters on graph embedding applied on symbolic graphs. In 12th IAPR International Workshop on Graphics Recognition.
Abstract: We propose an amelioration of proposed Graph Embedding (GEM) method in previous work that takes advantages of structural pattern representation and the structured distortion. it models an Attributed Graph (AG) as a Probabilistic Graphical Model (PGM). Then, it learns the parameters of this PGM presented by a vector, as new signature of AG in a lower dimensional vectorial space. We focus to adapt the structured learning algorithm via 1_slack formulation with a suitable risk function, called Graph Edit Distance (GED). It defines the dissimilarity of the ground truth and predicted graph labels. It determines by the error tolerant graph matching using bipartite graph matching algorithm. We apply Structured Support Vector Machines (SSVM) to process classification task. During our experiments, we got our results on the GREC dataset.
|
|
|
Jaume Gibert. (2009). Learning structural representations and graph matching paradigms in the context of object recognition (Vol. 143). Master's thesis, , .
|
|
|
Jose Marone, Simone Balocco, Marc Bolaños, Jose Massa, & Petia Radeva. (2016). Learning the Lumen Border using a Convolutional Neural Networks classifier. In 19th International Conference on Medical Image Computing and Computer Assisted Intervention Workshop.
Abstract: IntraVascular UltraSound (IVUS) is a technique allowing the diagnosis of coronary plaque. An accurate (semi-)automatic assessment of the luminal contours could speed up the diagnosis. In most of the approaches, the information on the vessel shape is obtained combining a supervised learning step with a local refinement algorithm. In this paper, we explore for the first time, the use of a Convolutional Neural Networks (CNN) architecture that on one hand is able to extract the optimal image features and at the same time can serve as a supervised classifier to detect the lumen border in IVUS images. The main limitation of CNN, relies on the fact that this technique requires a large amount of training data due to the huge amount of parameters that it has. To
solve this issue, we introduce a patch classification approach to generate an extended training-set from a few annotated images. An accuracy of 93% and F-score of 71% was obtained with this technique, even when it was applied to challenging frames containig calcified plaques, stents and catheter shadows.
|
|
|
Lichao Zhang, Abel Gonzalez-Garcia, Joost Van de Weijer, Martin Danelljan, & Fahad Shahbaz Khan. (2019). Learning the Model Update for Siamese Trackers. In 18th IEEE International Conference on Computer Vision (pp. 4009–4018).
Abstract: Siamese approaches address the visual tracking problem by extracting an appearance template from the current frame, which is used to localize the target in the next frame. In general, this template is linearly combined with the accumulated template from the previous frame, resulting in an exponential decay of information over time. While such an approach to updating has led to improved results, its simplicity limits the potential gain likely to be obtained by learning to update. Therefore, we propose to replace the handcrafted update function with a method which learns to update. We use a convolutional neural network, called UpdateNet, which given the initial template, the accumulated template and the template of the current frame aims to estimate the optimal template for the next frame. The UpdateNet is compact and can easily be integrated into existing Siamese trackers. We demonstrate the generality of the proposed approach by applying it to two Siamese trackers, SiamFC and DaSiamRPN. Extensive experiments on VOT2016, VOT2018, LaSOT, and TrackingNet datasets demonstrate that our UpdateNet effectively predicts the new target template, outperforming the standard linear update. On the large-scale TrackingNet dataset, our UpdateNet improves the results of DaSiamRPN with an absolute gain of 3.9% in terms of success score.
|
|
|
Mikel Menta, Adriana Romero, & Joost Van de Weijer. (2020). Learning to adapt class-specific features across domains for semantic segmentation.
Abstract: arXiv:2001.08311
Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any training annotations in this domain. The great majority of existing domain adaptation models rely on image translation networks, which often contain a huge amount of domain-specific parameters. Additionally, the feature adaptation step often happens globally, at a coarse level, hindering its applicability to tasks such as semantic segmentation, where details are of crucial importance to provide sharp results. In this thesis, we present a novel architecture, which learns to adapt features across domains by taking into account per class information. To that aim, we design a conditional pixel-wise discriminator network, whose output is conditioned on the segmentation masks. Moreover, following recent advances in image translation, we adopt the recently introduced StarGAN architecture as image translation backbone, since it is able to perform translations across multiple domains by means of a single generator network. Preliminary results on a segmentation task designed to assess the effectiveness of the proposed approach highlight the potential of the model, improving upon strong baselines and alternative designs.
|
|