arXiv subjects

Konstantinos Karantzalos

Publications and source records attributed to Konstantinos Karantzalos.

27 records · Page 2Linked to original sources

arXiv2023

Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?

Convolutional networks and vision transformers have different forms of pairwise interactions, pooling across layers and pooling at the end of the network. Does the latter really need to be different? As a by-product of pooling, vision transformers provide spatial attention for free, but this is most often of low quality unless self-supervised, which is not well studied. Is supervision really the problem? In this work, we develop a generic pooling framework and then we formulate a number of existing methods as instantiations. By discussing the properties of each group of methods, we derive SimPool, a simple attention-based pooling mechanism as a replacement of the default one for both convolutional and transformer encoders. We find that, whether supervised or self-supervised, this improves performance on pre-training and downstream tasks and provides attention maps delineating object boundaries in all cases. One could thus call SimPool universal. To our knowledge, we are the first to obtain attention maps in supervised transformers of at least as good quality as self-supervised, without explicit losses or modifying the architecture. Code at: https://github.com/billpsomas/simpool.

cs.CV↗

arXiv2022

Seafloor-Invariant Caustics Removal from Underwater Imagery

Mapping the seafloor with underwater imaging cameras is of significant importance for various applications including marine engineering, geology, geomorphology, archaeology and biology. For shallow waters, among the underwater imaging challenges, caustics i.e., the complex physical phenomena resulting from the projection of light rays being refracted by the wavy surface, is likely the most crucial one. Caustics is the main factor during underwater imaging campaigns that massively degrade image quality and affect severely any 2D mosaicking or 3D reconstruction of the seabed. In this work, we propose a novel method for correcting the radiometric effects of caustics on shallow underwater imagery. Contrary to the state-of-the-art, the developed method can handle seabed and riverbed of any anaglyph, correcting the images using real pixel information, thus, improving image matching and 3D reconstruction processes. In particular, the developed method employs deep learning architectures in order to classify image pixels to "non-caustics" and "caustics". Then, exploits the 3D geometry of the scene to achieve a pixel-wise correction, by transferring appropriate color values between the overlapping underwater images. Moreover, to fill the current gap, we have collected, annotated and structured a real-world caustic dataset, namely R-CAUSTIC, which is openly available. Overall, based on the experimental results and validation the developed methodology is quite promising in both detecting caustics and reconstructing their intensity.

cs.CV↗

arXiv2022

Objects Can Move: 3D Change Detection by Geometric Transformation Constistency

AR/VR applications and robots need to know when the scene has changed. An example is when objects are moved, added, or removed from the scene. We propose a 3D object discovery method that is based only on scene changes. Our method does not need to encode any assumptions about what is an object, but rather discovers objects by exploiting their coherent move. Changes are initially detected as differences in the depth maps and segmented as objects if they undergo rigid motions. A graph cut optimization propagates the changing labels to geometrically consistent regions. Experiments show that our method achieves state-of-the-art performance on the 3RScan dataset against competitive baselines. The source code of our method can be found at https://github.com/katadam/ObjectsCanMove.

cs.CV↗

arXiv2022

What to Hide from Your Students: Attention-Guided Masked Image Modeling

Transformers and masked language modeling are quickly being adopted and explored in computer vision as vision transformers and masked image modeling (MIM). In this work, we argue that image token masking differs from token masking in text, due to the amount and correlation of tokens in an image. In particular, to generate a challenging pretext task for MIM, we advocate a shift from random masking to informed masking. We develop and exhibit this idea in the context of distillation-based MIM, where a teacher transformer encoder generates an attention map, which we use to guide masking for the student. We thus introduce a novel masking strategy, called attention-guided masking (AttMask), and we demonstrate its effectiveness over random masking for dense distillation-based MIM as well as plain distillation-based self-supervised learning on classification tokens. We confirm that AttMask accelerates the learning process and improves the performance on a variety of downstream tasks. We provide the implementation code at https://github.com/gkakogeorgiou/attmask.

cs.CV↗

arXiv2022

It Takes Two to Tango: Mixup for Deep Metric Learning

Metric learning involves learning a discriminative representation such that embeddings of similar classes are encouraged to be close, while embeddings of dissimilar classes are pushed far apart. State-of-the-art methods focus mostly on sophisticated loss functions or mining strategies. On the one hand, metric learning losses consider two or more examples at a time. On the other hand, modern data augmentation methods for classification consider two or more examples at a time. The combination of the two ideas is under-studied. In this work, we aim to bridge this gap and improve representations using mixup, which is a powerful data augmentation approach interpolating two or more examples and corresponding target labels at a time. This task is challenging because unlike classification, the loss functions used in metric learning are not additive over examples, so the idea of interpolating target labels is not straightforward. To the best of our knowledge, we are the first to investigate mixing both examples and target labels for deep metric learning. We develop a generalized formulation that encompasses existing metric learning loss functions and modify it to accommodate for mixup, introducing Metric Mix, or Metrix. We also introduce a new metric - utilization, to demonstrate that by mixing examples during training, we are exploring areas of the embedding space beyond the training classes, thereby improving representations. To validate the effect of improved representations, we show that mixing inputs, intermediate representations or embeddings along with target labels significantly outperforms state-of-the-art metric learning methods on four benchmark deep metric learning datasets.

cs.LG↗

arXiv2021

Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensing

Although deep neural networks hold the state-of-the-art in several remote sensing tasks, their black-box operation hinders the understanding of their decisions, concealing any bias and other shortcomings in datasets and model performance. To this end, we have applied explainable artificial intelligence (XAI) methods in remote sensing multi-label classification tasks towards producing human-interpretable explanations and improve transparency. In particular, we utilized and trained deep learning models with state-of-the-art performance in the benchmark BigEarthNet and SEN12MS datasets. Ten XAI methods were employed towards understanding and interpreting models' predictions, along with quantitative metrics to assess and compare their performance. Numerous experiments were performed to assess the overall performance of XAI methods for straightforward prediction cases, competing multiple labels, as well as misclassification cases. According to our findings, Occlusion, Grad-CAM and Lime were the most interpretable and reliable XAI methods. However, none delivers high-resolution outputs, while apart from Grad-CAM, both Lime and Occlusion are computationally expensive. We also highlight different aspects of XAI performance and elaborate with insights on black-box decisions in order to improve transparency, understand their behavior and reveal, as well, datasets' particularities.

cs.LG↗

arXiv2020

Shallow Water Bathymetry Mapping from UAV Imagery based on Machine Learning

The determination of accurate bathymetric information is a key element for near offshore activities, hydrological studies such as coastal engineering applications, sedimentary processes, hydrographic surveying as well as archaeological mapping and biological research. UAV imagery processed with Structure from Motion (SfM) and Multi View Stereo (MVS) techniques can provide a low-cost alternative to established shallow seabed mapping techniques offering as well the important visual information. Nevertheless, water refraction poses significant challenges on depth determination. Till now, this problem has been addressed through customized image-based refraction correction algorithms or by modifying the collinearity equation. In this paper, in order to overcome the water refraction errors, we employ machine learning tools that are able to learn the systematic underestimation of the estimated depths. In the proposed approach, based on known depth observations from bathymetric LiDAR surveys, an SVR model was developed able to estimate more accurately the real depths of point clouds derived from SfM-MVS procedures. Experimental results over two test sites along with the performed quantitative validation indicated the high potential of the developed approach.

cs.CV↗

arXiv2019

Detecting Urban Changes with Recurrent Neural Networks from Multitemporal Sentinel-2 Data

\begin{abstract} The advent of multitemporal high resolution data, like the Copernicus Sentinel-2, has enhanced significantly the potential of monitoring the earth's surface and environmental dynamics. In this paper, we present a novel deep learning framework for urban change detection which combines state-of-the-art fully convolutional networks (similar to U-Net) for feature representation and powerful recurrent networks (such as LSTMs) for temporal modeling. We report our results on the recently publicly available bi-temporal Onera Satellite Change Detection (OSCD) Sentinel-2 dataset, enhancing the temporal information with additional images of the same region on different dates. Moreover, we evaluate the performance of the recurrent networks as well as the use of the additional dates on the unseen test-set using an ensemble cross-validation strategy. All the developed models during the validation phase have scored an overall accuracy of more than 95%, while the use of LSTMs and further temporal information, boost the F1 rate of the change class by an additional 1.5%.

cs.CV↗

arXiv2017

Building up user confidence for the spaceborne derived global and continental land cover products for the Mediterranean region: the case of Thessaly

Across globe and space agencies nations recognize the importance of homogenized land cover information, prone to regular updates, both in the context of thematic and spatial resolutions. Recent sensor advances and the free distribution policy promote the utilization of spaceborne products in an unprecedented pace into an increasingly wider range of applications. Ensuring credibility to the users is a major enabler in this process. To this end this study contributes with a systematic accuracy performance measurement and continental/global land cover layers' inter-comparison moving towards confidence built up. Confidence levels during validation and a weighted overall accuracy assessment were applied. Google Earth imagery was employed to assess the accuracy of three land cover products, i.e., Globeland30, HRLs and CLC 2012, for the years 2010 and 2012. Reported rates indicate a minimum weighted overall accuracy of 84%. Specific classes' performance deviations from the general trend were noted and discussed on the basis of an unbiased sampling approach. By integrating confidence levels during the ground truth annotation, stratified sampling on the several Corine Level 3 subclasses and the weighted overall accuracy assessment, the different aspects of the considered land cover products can be highlighted more objectively.

cs.OH↗