|
|
Azadeh S. Mozafari, David Vazquez, Mansour Jamzad, & Antonio Lopez. (2016). Node-Adapt, Path-Adapt and Tree-Adapt:Model-Transfer Domain Adaptation for Random Forest.
Abstract: Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency. However, as many other classifiers, RF requires domain adaptation (DA) provided that there is a mismatch between the training (source) and testing (target) domains which provokes classification degradation. Consequently, different RF-DA methods have been proposed, which not only require target-domain samples but revisiting the source-domain ones, too. As novelty, we propose three inherently different methods (Node-Adapt, Path-Adapt and Tree-Adapt) that only require the learned source-domain RF and a relatively few target-domain samples for DA, i.e. source-domain samples do not need to be available. To assess the performance of our proposals we focus on image-based object detection, using the pedestrian detection problem as challenging proof-of-concept. Moreover, we use the RF with expert nodes because it is a competitive patch-based pedestrian model. We test our Node-, Path- and Tree-Adapt methods in standard benchmarks, showing that DA is largely achieved.
Keywords: Domain Adaptation; Pedestrian detection; Random Forest
|
|
|
|
Ayan Banerjee, Sanket Biswas, Josep Llados, & Umapada Pal. (2024). GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation.
Abstract: Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements. Large and complex models, while achieving high accuracy, can be computationally expensive and memory-intensive, making them impractical for deployment on resource constrained devices. Knowledge distillation allows us to create small and more efficient models that retain much of the performance of their larger counterparts. Here we present a graph-based knowledge distillation framework to correctly identify and localize the document objects in a document image. Here, we design a structured graph with nodes containing proposal-level features and edges representing the relationship between the different proposal regions. Also, to reduce text bias an adaptive node sampling strategy is designed to prune the weight distribution and put more weightage on non-text nodes. We encode the complete graph as a knowledge representation and transfer it from the teacher to the student through the proposed distillation loss by effectively capturing both local and global information concurrently. Extensive experimentation on competitive benchmarks demonstrates that the proposed framework outperforms the current state-of-the-art approaches. The code will be available at: this https URL.
|
|
|
|
Arya Farkhondeh, Cristina Palmero, Simone Scardapane, & Sergio Escalera. (2022). Towards Self-Supervised Gaze Estimation.
Abstract: Recent joint embedding-based self-supervised methods have surpassed standard supervised approaches on various image recognition tasks such as image classification. These self-supervised methods aim at maximizing agreement between features extracted from two differently transformed views of the same image, which results in learning an invariant representation with respect to appearance and geometric image transformations. However, the effectiveness of these approaches remains unclear in the context of gaze estimation, a structured regression task that requires equivariance under geometric transformations (e.g., rotations, horizontal flip). In this work, we propose SwAT, an equivariant version of the online clustering-based self-supervised approach SwAV, to learn more informative representations for gaze estimation. We demonstrate that SwAT, with ResNet-50 and supported with uncurated unlabeled face images, outperforms state-of-the-art gaze estimation methods and supervised baselines in various experiments. In particular, we achieve up to 57% and 25% improvements in cross-dataset and within-dataset evaluation tasks on existing benchmarks (ETH-XGaze, Gaze360, and MPIIFaceGaze).
|
|
|
|
Antonio Lopez, W. Niessen, Joan Serrat, K. Nicolay, Bart M. Ter Haar Romeny, Juan J. Villanueva, et al. (1999). New improvements in the multiscale analysis of trabecular bone patterns..
|
|
|
|
Antonio Lopez, W. Niessen, Joan Serrat, K. Nicolay, Bart M. Ter Haar Romeny, Juan J. Villanueva, et al. (2000). New improvements in the multiscale analysis of trabecular bone patterns..
|
|
|
|
Antonio Lopez, Ricardo Toledo, Joan Serrat, & Juan J. Villanueva. (1999). Extraction of vessel centerlines from 2D coronary angiographies.
|
|
|
|
Antonio Lopez, Joan Serrat, J. Saludes, Cristina Cañero, Felipe Lumbreras, & T. Graf. (2005). Ridgeness for Detecting Lane Markings.
|
|
|
|
Antonio Lopez, & Joan Serrat. (1996). Tracing crease curves by solving a system of differential equations..
|
|
|
|
Antonio Lopez, & Joan Serrat. (1995). Image Analysis through Surface Geometric Descriptors.
|
|
|
|
Antonio Lopez, J. Hilgenstock, A. Busse, Ramon Baldrich, Felipe Lumbreras, & Joan Serrat. (2008). Temporal Coherence Analysis for Intelligent Headlight Control.
Keywords: Intelligent Headlights
|
|
|
|
Antonio Lopez, Felipe Lumbreras, Joan Serrat, & Juan J. Villanueva. (1999). Evaluation of Methods for Ridge and Valley Detection.
|
|
|
|
Antonio Lopez, Felipe Lumbreras, & Joan Serrat. (1998). Creaseness form level set extrinsec curvature..
|
|
|
|
Antonio Lopez, Felipe Lumbreras, A. Martinez, Joan Serrat, Xavier Roca, Javier Varona, et al. (1997). Aplicaciones de la vision por computador a la industria..
|
|
|
|
Antonio Lopez, David Lloret, Joan Serrat, & Juan J. Villanueva. (2000). Multilocal Creaseness Based on the Level-Set Extrinsic Curvarture..
|
|
|
|
Antonio Lopez, David Lloret, & Joan Serrat. (1998). Creaseness measures for CT and MR image registration..
Abstract: Creases are a type of ridge/valley structures that can be characterized by local conditions. Therefore, creaseness refers to local ridgeness and valleyness. The curvature K of the level curves and the mean curvature kM of the level surfaces are good measures of creaseness for 2-d and 3-d images, respectively. However, the way they are computed gives rise to discontinuities, reducing their usefulness in many applications. We propose a new creaseness measure, based on these curvatures, that avoids the discontinuities. We demonstrate its usefulness in the registration of CT and MR brain volumes, from the same patient, by searching the maximum in the correlation of their creaseness responses (ridgeness from the CT and valleyness from the MR). Due to the high dimensionality of the space of transforms, the search is performed by a hierarchical approach combined with an optimization method at each level of the hierarchy
|
|
