Alona Golts
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alona Golts has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Michael Elad
Technion -Israel Institute of Technology Haifa Israel
7 shared publications - Daniel Freedman
Google Research, Haifa, Israel
3 shared publications - Aaron Ciechanover
The Rappaport Technion Integrated Cancer Center (R-TICC) and the Rappaport Faculty of Medicine and Research Institute, Technion-Israel Institute of Technology, Haifa, Israel
1 shared publication - Aviad Aberdam
Department of Statistics Electrical Engineering Sulam Biomedical Engineering Computer Science Stanford University Technion -Israel Institute of Technol- ogy Johns Hopkins University Technion -Israel Institute of Technology
1 shared publication - Aviad Aberdam1 shared publication
Daniel Freedman
Google Research, Haifa, Israel
1 shared publication
Latest Publications
- 18 February 2023
- Published by Springer Nature
- p. 313-329
Simultaneous Detection and Classification of Partially and Weakly Supervised Cells
- 18 February 2023
- Published by Springer Nature
- p. 313-329
Simultaneous Detection and Classification of Partially and Weakly Supervised Cells
- 4 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (12) , 9222-9235
Ada-LISTA: Learned Solvers Adaptive to Varying Models
Neural networks that are based on the unfolding of iterative solvers as LISTA (Learned Iterative Soft Shrinkage), are widely used due to their accelerated performance. These networks, trained with a fixed dictionary, are inapplicable in varying model scenarios, as opposed to their flexible non-learned counterparts. We introduce, Ada-LISTA, an adaptive learned solver which receives as input both the signal and its corresponding dictionary, and learns a universal architecture to serve them all. This scheme allows solving sparse coding in linear rate, under varying models, including permutations and perturbations of the dictionary. We provide an extensive theoretical and numerical study, demonstrating the adaptation capabilities of our approach, and its application to the task of natural image inpainting.
- 4 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (12) , 9222-9235
Ada-LISTA: Learned Solvers Adaptive to Varying Models
Neural networks that are based on the unfolding of iterative solvers as LISTA (Learned Iterative Soft Shrinkage), are widely used due to their accelerated performance. These networks, trained with a fixed dictionary, are inapplicable in varying model scenarios, as opposed to their flexible non-learned counterparts. We introduce, Ada-LISTA, an adaptive learned solver which receives as input both the signal and its corresponding dictionary, and learns a universal architecture to serve them all. This scheme allows solving sparse coding in linear rate, under varying models, including permutations and perturbations of the dictionary. We provide an extensive theoretical and numerical study, demonstrating the adaptation capabilities of our approach, and its application to the task of natural image inpainting.
- 6 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 15 (2) , 324-338
Deep Energy: Task Driven Training of Deep Neural Networks
The current gold standard in solving image processing and computer vision tasks is using supervised learning of deep neural networks (DNNs), requiring large-scale datasets of input-output pairs. In many scenarios in which the output is an image -- e.g., medical image analysis, image denoising, deblurring, super-resolution, dehazing, segmentation and optical flow estimation -- the collection of labelled image pairs for training is either time-consuming or limited to simple degradation models. Indeed, there is an increasing body of work targeted at weakly supervised training, accompanied with different unsupervised loss functions. This work dives into the regime of "Deep-Energy", a task-driven training approach that substitutes the generic loss with minimization of energy functions using DNNs. Such energy functions, often formulated as a combination of a data-fidelity term along with an application-specific prior, are essentially unsupervised as they do not assume knowledge of the output image. As opposed to classic energy minimization, where computationally-intensive inference is performed for each new image, our network, once trained, can compute the output with a single forward-pass operation. By incorporating application-specific domain knowledge to the loss function, we are able to use real-world images, thus decreasing the dependency on pixel-wise labelled data or synthetic datasets. We demonstrate our approach on three different applications: seeded segmentation, image matting and single image dehazing, showing clear benefits of both speedup and improved accuracy versus the classical energy minimization approach, and competitive performance with respect to fully supervised alternatives.
- 6 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 15 (2) , 324-338
Deep Energy: Task Driven Training of Deep Neural Networks
The current gold standard in solving image processing and computer vision tasks is using supervised learning of deep neural networks (DNNs), requiring large-scale datasets of input-output pairs. In many scenarios in which the output is an image -- e.g., medical image analysis, image denoising, deblurring, super-resolution, dehazing, segmentation and optical flow estimation -- the collection of labelled image pairs for training is either time-consuming or limited to simple degradation models. Indeed, there is an increasing body of work targeted at weakly supervised training, accompanied with different unsupervised loss functions. This work dives into the regime of "Deep-Energy", a task-driven training approach that substitutes the generic loss with minimization of energy functions using DNNs. Such energy functions, often formulated as a combination of a data-fidelity term along with an application-specific prior, are essentially unsupervised as they do not assume knowledge of the output image. As opposed to classic energy minimization, where computationally-intensive inference is performed for each new image, our network, once trained, can compute the output with a single forward-pass operation. By incorporating application-specific domain knowledge to the loss function, we are able to use real-world images, thus decreasing the dependency on pixel-wise labelled data or synthetic datasets. We demonstrate our approach on three different applications: seeded segmentation, image matting and single image dehazing, showing clear benefits of both speedup and improved accuracy versus the classical energy minimization approach, and competitive performance with respect to fully supervised alternatives.
- Open Access
Ada-LISTA: Learned Solvers Adaptive to Varying Models
Neural networks that are based on unfolding of an iterative solver, such as LISTA (learned iterative soft threshold algorithm), are widely used due to their accelerated performance. Nevertheless, as opposed to non-learned solvers, these networks are trained on a certain dictionary, and therefore they are inapplicable for varying model scenarios. This work introduces an adaptive learned solver, termed Ada-LISTA, which receives pairs of signals and their corresponding dictionaries as inputs, and learns a universal architecture to serve them all. We prove that this scheme is guaranteed to solve sparse coding in linear rate for varying models, including dictionary perturbations and permutations. We also provide an extensive numerical study demonstrating its practical adaptation capabilities. Finally, we deploy Ada-LISTA to natural image inpainting, where the patch-masks vary spatially, thus requiring such an adaptation.
Open AccessAda-LISTA: Learned Solvers Adaptive to Varying Models
Neural networks that are based on unfolding of an iterative solver, such as LISTA (learned iterative soft threshold algorithm), are widely used due to their accelerated performance. Nevertheless, as opposed to non-learned solvers, these networks are trained on a certain dictionary, and therefore they are inapplicable for varying model scenarios. This work introduces an adaptive learned solver, termed Ada-LISTA, which receives pairs of signals and their corresponding dictionaries as inputs, and learns a universal architecture to serve them all. We prove that this scheme is guaranteed to solve sparse coding in linear rate for varying models, including dictionary perturbations and permutations. We also provide an extensive numerical study demonstrating its practical adaptation capabilities. Finally, we deploy Ada-LISTA to natural image inpainting, where the patch-masks vary spatially, thus requiring such an adaptation.
- 12 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 2692-2701
Unsupervised Single Image Dehazing Using Dark Channel Prior Loss
Single image dehazing is a critical stage in many modern-day autonomous vision applications. Early prior-based methods often involved a time-consuming minimization of a hand-crafted energy function. Recent learning-based approaches utilize the representational power of deep neural networks (DNNs) to learn the underlying transformation between hazy and clear images. Due to inherent limitations in collecting matching clear and hazy images, these methods resort to training on synthetic data, constructed from indoor images and corresponding depth information. This may result in a possible domain shift when treating outdoor scenes. We propose a completely unsupervised method of training via minimization of the well-known, Dark Channel Prior (DCP) energy function. Instead of feeding the network with synthetic data, we solely use real-world outdoor images and tune the network's parameters by directly minimizing the DCP. Although our “Deep DCP” technique can be regarded as a fast approximator of DCP, it actually improves its results significantly. This suggests an additional regularization obtained via the network and learning process. Experiments show that our method performs on par with large-scale supervised methods.
- 12 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 2692-2701
Unsupervised Single Image Dehazing Using Dark Channel Prior Loss
Single image dehazing is a critical stage in many modern-day autonomous vision applications. Early prior-based methods often involved a time-consuming minimization of a hand-crafted energy function. Recent learning-based approaches utilize the representational power of deep neural networks (DNNs) to learn the underlying transformation between hazy and clear images. Due to inherent limitations in collecting matching clear and hazy images, these methods resort to training on synthetic data, constructed from indoor images and corresponding depth information. This may result in a possible domain shift when treating outdoor scenes. We propose a completely unsupervised method of training via minimization of the well-known, Dark Channel Prior (DCP) energy function. Instead of feeding the network with synthetic data, we solely use real-world outdoor images and tune the network's parameters by directly minimizing the DCP. Although our “Deep DCP” technique can be regarded as a fast approximator of DCP, it actually improves its results significantly. This suggests an additional regularization obtained via the network and learning process. Experiments show that our method performs on par with large-scale supervised methods.
- Open Access
Unsupervised Single Image Dehazing Using Dark Channel Prior Loss
Single image dehazing is a critical stage in many modern-day autonomous vision applications. Early prior-based methods often involved a time-consuming minimization of a hand-crafted energy function. Recent learning-based approaches utilize the representational power of deep neural networks (DNNs) to learn the underlying transformation between hazy and clear images. Due to inherent limitations in collecting matching clear and hazy images, these methods resort to training on synthetic data; constructed from indoor images and corresponding depth information. This may result in a possible domain shift when treating outdoor scenes. We propose a completely unsupervised method of training via minimization of the well-known, Dark Channel Prior (DCP) energy function. Instead of feeding the network with synthetic data, we solely use real-world outdoor images and tune the network's parameters by directly minimizing the DCP. Although our "Deep DCP" technique can be regarded as a fast approximator of DCP, it actually improves its results significantly. This suggests an additional regularization obtained via the network and learning process. Experiments show that our method performs on par with large-scale supervised methods.
Open AccessUnsupervised Single Image Dehazing Using Dark Channel Prior Loss
Single image dehazing is a critical stage in many modern-day autonomous vision applications. Early prior-based methods often involved a time-consuming minimization of a hand-crafted energy function. Recent learning-based approaches utilize the representational power of deep neural networks (DNNs) to learn the underlying transformation between hazy and clear images. Due to inherent limitations in collecting matching clear and hazy images, these methods resort to training on synthetic data; constructed from indoor images and corresponding depth information. This may result in a possible domain shift when treating outdoor scenes. We propose a completely unsupervised method of training via minimization of the well-known, Dark Channel Prior (DCP) energy function. Instead of feeding the network with synthetic data, we solely use real-world outdoor images and tune the network's parameters by directly minimizing the DCP. Although our "Deep DCP" technique can be regarded as a fast approximator of DCP, it actually improves its results significantly. This suggests an additional regularization obtained via the network and learning process. Experiments show that our method performs on par with large-scale supervised methods.
- Open Access
Deep-Energy: Unsupervised Training of Deep Neural Networks
The success of deep learning has been due, in no small part, to the availability of large annotated datasets. Thus, a major bottleneck in current learning pipelines is the time-consuming human annotation of data. In scenarios where such input-output pairs cannot be collected, simulation is often used instead, leading to a domain-shift between synthesized and real-world data. This work offers an unsupervised alternative that relies on the availability of task-specific energy functions, replacing the generic supervised loss. Such energy functions are assumed to lead to the desired label as their minimizer given the input. The proposed approach, termed "Deep Energy", trains a Deep Neural Network (DNN) to approximate this minimization for any chosen input. Once trained, a simple and fast feed-forward computation provides the inferred label. This approach allows us to perform unsupervised training of DNNs with real-world inputs only, and without the need for manually-annotated labels, nor synthetically created data. "Deep Energy" is demonstrated in this paper on three different tasks -- seeded segmentation, image matting and single image dehazing -- exposing its generality and wide applicability. Our experiments show that the solution provided by the network is often much better in quality than the one obtained by a direct minimization of the energy function, suggesting an added regularization property in our scheme.
Open AccessDeep-Energy: Unsupervised Training of Deep Neural Networks
The success of deep learning has been due, in no small part, to the availability of large annotated datasets. Thus, a major bottleneck in current learning pipelines is the time-consuming human annotation of data. In scenarios where such input-output pairs cannot be collected, simulation is often used instead, leading to a domain-shift between synthesized and real-world data. This work offers an unsupervised alternative that relies on the availability of task-specific energy functions, replacing the generic supervised loss. Such energy functions are assumed to lead to the desired label as their minimizer given the input. The proposed approach, termed "Deep Energy", trains a Deep Neural Network (DNN) to approximate this minimization for any chosen input. Once trained, a simple and fast feed-forward computation provides the inferred label. This approach allows us to perform unsupervised training of DNNs with real-world inputs only, and without the need for manually-annotated labels, nor synthetically created data. "Deep Energy" is demonstrated in this paper on three different tasks -- seeded segmentation, image matting and single image dehazing -- exposing its generality and wide applicability. Our experiments show that the solution provided by the network is often much better in quality than the one obtained by a direct minimization of the energy function, suggesting an added regularization property in our scheme.
- 20 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 10 (4) , 726-739
Linearized Kernel Dictionary Learning
In this paper, we present a new approach of incorporating kernels into dictionary learning. The kernel K-SVD algorithm (KKSVD), which has been introduced recently, shows an improvement in classification performance, with relation to its linear counterpart K-SVD. However, this algorithm requires the storage and handling of a very large kernel matrix, which leads to high computational cost, while also limiting its use to setups with small number of training examples. We address these problems by combining two ideas: first, we approximate the kernel matrix using a cleverly sampled subset of its columns using the Nyström method; second, as we wish to avoid using this matrix altogether, we decompose it by SVD to form new “virtual samples,” on which any linear dictionary learning can be employed. Our method, termed “Linearized Kernel Dictionary Learning” (LKDL) can be seamlessly applied as a preprocessing stage on top of any efficient off-the-shelf dictionary learning scheme, effectively “kernelizing” it. We demonstrate the effectiveness of our method on several tasks of both supervised and unsupervised classification and show the efficiency of the proposed scheme, its easy integration and performance boosting properties.
- 20 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 10 (4) , 726-739
Linearized Kernel Dictionary Learning
In this paper, we present a new approach of incorporating kernels into dictionary learning. The kernel K-SVD algorithm (KKSVD), which has been introduced recently, shows an improvement in classification performance, with relation to its linear counterpart K-SVD. However, this algorithm requires the storage and handling of a very large kernel matrix, which leads to high computational cost, while also limiting its use to setups with small number of training examples. We address these problems by combining two ideas: first, we approximate the kernel matrix using a cleverly sampled subset of its columns using the Nyström method; second, as we wish to avoid using this matrix altogether, we decompose it by SVD to form new “virtual samples,” on which any linear dictionary learning can be employed. Our method, termed “Linearized Kernel Dictionary Learning” (LKDL) can be seamlessly applied as a preprocessing stage on top of any efficient off-the-shelf dictionary learning scheme, effectively “kernelizing” it. We demonstrate the effectiveness of our method on several tasks of both supervised and unsupervised classification and show the efficiency of the proposed scheme, its easy integration and performance boosting properties.