|
Joakim Bruslund Haurum, Sergio Escalera, Graham W. Taylor, & Thomas B. (2023). Which Tokens to Use? Investigating Token Reduction in Vision Transformers. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops.
Abstract: Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs more efficient by removing redundant information in the processed tokens. While different methods have been explored to achieve this goal, we still lack understanding of the resulting reduction patterns and how those patterns differ across token reduction methods and datasets. To close this gap, we set out to understand the reduction patterns of 10 different token reduction methods using four image classification datasets. By systematically comparing these methods on the different classification tasks, we find that the Top-K pruning method is a surprisingly strong baseline. Through in-depth analysis of the different methods, we determine that: the reduction patterns are generally not consistent when varying the capacity of the backbone model, the reduction patterns of pruning-based methods significantly differ from fixed radial patterns, and the reduction patterns of pruning-based methods are correlated across classification datasets. Finally we report that the similarity of reduction patterns is a moderate-to-strong proxy for model performance. Project page at https://vap.aau.dk/tokens.
|
|
|
Patricia Marquez, Debora Gil, Aura Hernandez-Sabate, & Daniel Kondermann. (2013). When Is A Confidence Measure Good Enough? In 9th International Conference on Computer Vision Systems (Vol. 7963, pp. 344–353). LNCS. Springer Link.
Abstract: Confidence estimation has recently become a hot topic in image processing and computer vision.Yet, several definitions exist of the term “confidence” which are sometimes used interchangeably. This is a position paper, in which we aim to give an overview on existing definitions,
thereby clarifying the meaning of the used terms to facilitate further research in this field. Based on these clarifications, we develop a theory to compare confidence measures with respect to their quality.
Keywords: Optical flow, confidence measure, performance evaluation
|
|
|
Javad Zolfaghari Bengar, Bogdan Raducanu, & Joost Van de Weijer. (2021). When Deep Learners Change Their Mind: Learning Dynamics for Active Learning. In 19th International Conference on Computer Analysis of Images and Patterns (Vol. 13052, pp. 403–413).
Abstract: Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the certainty of the network predictions for samples. However, it is well-known that neural networks are overly confident about their prediction and are therefore an untrustworthy source to assess sample informativeness. In this paper, we propose a new informativeness-based active learning method. Our measure is derived from the learning dynamics of a neural network. More precisely we track the label assignment of the unlabeled data pool during the training of the algorithm. We capture the learning dynamics with a metric called label-dispersion, which is low when the network consistently assigns the same label to the sample during the training of the network and high when the assigned label changes frequently. We show that label-dispersion is a promising predictor of the uncertainty of the network, and show on two benchmark datasets that an active learning algorithm based on label-dispersion obtains excellent results.
|
|
|
Olivier Penacchio, & C. Alejandro Parraga. (2011). What is the best criterion for an efficient design of retinal photoreceptor mosaics? PER - Perception, 40, 197.
Abstract: The proportions of L, M and S photoreceptors in the primate retina are arguably determined by evolutionary pressure and the statistics of the visual environment. Two information theory-based approaches have been recently proposed for explaining the asymmetrical spatial densities of photoreceptors in humans. In the first approach Garrigan et al (2010 PLoS ONE 6 e1000677), a model for computing the information transmitted by cone arrays which considers the differential blurring produced by the long-wavelength accommodation of the eye’s lens is proposed. Their results explain the sparsity of S-cones but the optimum depends weakly on the L:M cone ratio. In the second approach (Penacchio et al, 2010 Perception 39 ECVP Supplement, 101), we show that human cone arrays make the visual representation scale-invariant, allowing the total entropy of the signal to be preserved while decreasing individual neurons’ entropy in further retinotopic representations. This criterion provides a thorough description of the distribution of L:M cone ratios and does not depend on differential blurring of the signal by the lens. Here, we investigate the similarities and differences of both approaches when applied to the same database. Our results support a 2-criteria optimization in the space of cone ratios whose components are arguably important and mostly unrelated.
[This work was partially funded by projects TIN2010-21771-C02-1 and Consolider-Ingenio 2010-CSD2007-00018 from the Spanish MICINN. CAP was funded by grant RYC-2007-00484]
|
|
|
Jordi Roca, Maria Vanrell, & C. Alejandro Parraga. (2012). What is constant in colour constancy? In 6th European Conference on Colour in Graphics, Imaging and Vision (pp. 337–343).
Abstract: Color constancy refers to the ability of the human visual system to stabilize
the color appearance of surfaces under an illuminant change. In this work we studied how the interrelations among nine colors are perceived under illuminant changes, particularly whether they remain stable across 10 different conditions (5 illuminants and 2 backgrounds). To do so we have used a paradigm that measures several colors under an immersive state of adaptation. From our measures we defined a perceptual structure descriptor that is up to 87% stable over all conditions, suggesting that color category features could be used to predict color constancy. This is in agreement with previous results on the stability of border categories [1,2] and with computational color constancy
algorithms [3] for estimating the scene illuminant.
|
|
|
Ciprian Corneanu, Meysam Madadi, Sergio Escalera, & Aleix M. Martinez. (2019). What does it mean to learn in deep networks? And, how does one detect adversarial attacks? In 32nd IEEE Conference on Computer Vision and Pattern Recognition (pp. 4752–4761).
Abstract: The flexibility and high-accuracy of Deep Neural Networks (DNNs) has transformed computer vision. But, the fact that we do not know when a specific DNN will work and when it will fail has resulted in a lack of trust. A clear example is self-driving cars; people are uncomfortable sitting in a car driven by algorithms that may fail under some unknown, unpredictable conditions. Interpretability and explainability approaches attempt to address this by uncovering what a DNN models, i.e., what each node (cell) in the network represents and what images are most likely to activate it. This can be used to generate, for example, adversarial attacks. But these approaches do not generally allow us to determine where a DNN will succeed or fail and why. i.e., does this learned representation generalize to unseen samples? Here, we derive a novel approach to define what it means to learn in deep networks, and how to use this knowledge to detect adversarial attacks. We show how this defines the ability of a network to generalize to unseen testing samples and, most importantly, why this is the case.
|
|
|
R. Valenti, N. Sebe, & Theo Gevers. (2012). What are you looking at? Improving Visual gaze Estimation by Saliency. IJCV - International Journal of Computer Vision, 98(3), 324–334.
Abstract: Impact factor 2010: 5.15
Impact factor 2011/12?: 5.36
In this paper we present a novel mechanism to obtain enhanced gaze estimation for subjects looking at a scene or an image. The system makes use of prior knowledge about the scene (e.g. an image on a computer screen), to define a probability map of the scene the subject is gazing at, in order to find the most probable location. The proposed system helps in correcting the fixations which are erroneously estimated by the gaze estimation device by employing a saliency framework to adjust the resulting gaze point vector. The system is tested on three scenarios: using eye tracking data, enhancing a low accuracy webcam based eye tracker, and using a head pose tracker. The correlation between the subjects in the commercial eye tracking data is improved by an average of 13.91%. The correlation on the low accuracy eye gaze tracker is improved by 59.85%, and for the head pose tracker we obtain an improvement of 10.23%. These results show the potential of the system as a way to enhance and self-calibrate different visual gaze estimation systems.
|
|
|
Debora Gil, Agnes Borras, Ruth Aris, Mariano Vazquez, Pierre Lafortune, & Guillame Houzeaux. (2012). What a difference in biomechanics cardiac fiber makes. In Statistical Atlases And Computational Models Of The Heart: Imaging and Modelling Challenges (Vol. 7746, pp. 253–260). Springer Berlin Heidelberg.
Abstract: Computational simulations of the heart are a powerful tool for a comprehensive understanding of cardiac function and its intrinsic relationship with its muscular architecture. Cardiac biomechanical models require a vector field representing the orientation of cardiac fibers. A wrong orientation of the fibers can lead to a
non-realistic simulation of the heart functionality. In this paper we explore the impact of the fiber information on the simulated biomechanics of cardiac muscular anatomy. We have used the John Hopkins database to perform a biomechanical simulation using both a synthetic benchmark fiber distribution and the data obtained experimentally from DTI. Results illustrate how differences in fiber orientation affect heart deformation along cardiac cycle.
|
|
|
David Guillamet, M. Bressan, & Jordi Vitria. (2001). Weighted Non-negative Matrix Factorization for Local Representations..
|
|
|
Xavier Baro, & Jordi Vitria. (2008). Weighted Dissociated Diploes: An Extended Visual Feature Set. In Computer Vision Systems. 6th International Conference ICVS (Vol. 5008, 281–290). LNCS.
|
|
|
Santiago Segui, Laura Igual, & Jordi Vitria. (2010). Weighted Bagging for Graph based One-Class Classifiers. In 9th International Workshop on Multiple Classifier Systems (Vol. 5997, pp. 1–10). LNCS. Springer Berlin Heidelberg.
Abstract: Most conventional learning algorithms require both positive and negative training data for achieving accurate classification results. However, the problem of learning classifiers from only positive data arises in many applications where negative data are too costly, difficult to obtain, or not available at all. Minimum Spanning Tree Class Descriptor (MSTCD) was presented as a method that achieves better accuracies than other one-class classifiers in high dimensional data. However, the presence of outliers in the target class severely harms the performance of this classifier. In this paper we propose two bagging strategies for MSTCD that reduce the influence of outliers in training data. We show the improved performance on both real and artificially contaminated data.
|
|
|
Saad Minhas, Zeba Khanam, Shoaib Ehsan, Klaus McDonald Maier, & Aura Hernandez-Sabate. (2022). Weather Classification by Utilizing Synthetic Data. SENS - Sensors, 22(9), 3193.
Abstract: Weather prediction from real-world images can be termed a complex task when targeting classification using neural networks. Moreover, the number of images throughout the available datasets can contain a huge amount of variance when comparing locations with the weather those images are representing. In this article, the capabilities of a custom built driver simulator are explored specifically to simulate a wide range of weather conditions. Moreover, the performance of a new synthetic dataset generated by the above simulator is also assessed. The results indicate that the use of synthetic datasets in conjunction with real-world datasets can increase the training efficiency of the CNNs by as much as 74%. The article paves a way forward to tackle the persistent problem of bias in vision-based datasets.
Keywords: Weather classification; synthetic data; dataset; autonomous car; computer vision; advanced driver assistance systems; deep learning; intelligent transportation systems
|
|
|
Idoia Ruiz, Lorenzo Porzi, Samuel Rota Bulo, Peter Kontschieder, & Joan Serrat. (2021). Weakly Supervised Multi-Object Tracking and Segmentation. In IEEE Winter Conference on Applications of Computer Vision Workshops (pp. 125–133).
Abstract: We introduce the problem of weakly supervised MultiObject Tracking and Segmentation, i.e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation.
To address it, we design a novel synergistic training strategy by taking advantage of multi-task learning, i.e. classification and tracking tasks guide the training of the unsupervised instance segmentation. For that purpose, we extract weak foreground localization information, provided by
Grad-CAM heatmaps, to generate a partial ground truth to learn from. Additionally, RGB image level information is employed to refine the mask prediction at the edges of the
objects. We evaluate our method on KITTI MOTS, the most representative benchmark for this task, reducing the performance gap on the MOTSP metric between the fully supervised and weakly supervised approach to just 12% and 12.7 % for cars and pedestrians, respectively.
|
|
|
Lu Yu, Yongmei Cheng, & Joost Van de Weijer. (2018). Weakly Supervised Domain-Specific Color Naming Based on Attention. In 24th International Conference on Pattern Recognition (pp. 3019–3024).
Abstract: The majority of existing color naming methods focuses on the eleven basic color terms of the English language. However, in many applications, different sets of color names are used for the accurate description of objects. Labeling data to learn these domain-specific color names is an expensive and laborious task. Therefore, in this article we aim to learn color names from weakly labeled data. For this purpose, we add an attention branch to the color naming network. The attention branch is used to modulate the pixel-wise color naming predictions of the network. In experiments, we illustrate that the attention branch correctly identifies the relevant regions. Furthermore, we show that our method obtains state-of-the-art results for pixel-wise and image-wise classification on the EBAY dataset and is able to learn color names for various domains.
|
|
|
David Vazquez, Jiaolong Xu, Sebastian Ramos, Antonio Lopez, & Daniel Ponsa. (2013). Weakly Supervised Automatic Annotation of Pedestrian Bounding Boxes. In CVPR Workshop on Ground Truth – What is a good dataset? (pp. 706–711). IEEE.
Abstract: Among the components of a pedestrian detector, its trained pedestrian classifier is crucial for achieving the desired performance. The initial task of the training process consists in collecting samples of pedestrians and background, which involves tiresome manual annotation of pedestrian bounding boxes (BBs). Thus, recent works have assessed the use of automatically collected samples from photo-realistic virtual worlds. However, learning from virtual-world samples and testing in real-world images may suffer the dataset shift problem. Accordingly, in this paper we assess an strategy to collect samples from the real world and retrain with them, thus avoiding the dataset shift, but in such a way that no BBs of real-world pedestrians have to be provided. In particular, we train a pedestrian classifier based on virtual-world samples (no human annotation required). Then, using such a classifier we collect pedestrian samples from real-world images by detection. After, a human oracle rejects the false detections efficiently (weak annotation). Finally, a new classifier is trained with the accepted detections. We show that this classifier is competitive with respect to the counterpart trained with samples collected by manually annotating hundreds of pedestrian BBs.
Keywords: Pedestrian Detection; Domain Adaptation
|
|