More Like this

1. Benefits of Synthetically Pre-trained Depth-Prediction Networks for Indoor/Outdoor Image Classification

   https://doi.org/10.1109/WACVW58289.2023.00040  

   Lin, Kelly X.; Cho, Irene; Walimbe, Amey; Zamora, Bryan A.; Rich, Alex; Zhang, Sirius Z.; Höllerer, Tobias (January 2023, 2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW))

   Ground truth depth information is necessary for many computer vision tasks. Collecting this information is chal-lenging, especially for outdoor scenes. In this work, we propose utilizing single-view depth prediction neural networks pre-trained on synthetic scenes to generate relative depth, which we call pseudo-depth. This approach is a less expen-sive option as the pre-trained neural network obtains ac-curate depth information from synthetic scenes, which does not require any expensive sensor equipment and takes less time. We measure the usefulness of pseudo-depth from pre-trained neural networks by training indoor/outdoor binary classifiers with and without it. We also compare the difference in accuracy between using pseudo-depth and ground truth depth. We experimentally show that adding pseudo-depth to training achieves a 4.4% performance boost over the non-depth baseline model on DIODE, a large stan-dard test dataset, retaining 63.8% of the performance boost achieved from training a classifier on RGB and ground truth depth. It also boosts performance by 1.3% on another dataset, SUN397, for which ground truth depth is not avail-able. Our result shows that it is possible to take information obtained from a model pre-trained on synthetic scenes and successfully apply it beyond the synthetic domain to real-world data. 

   more » « less
2. Image classification and training with severe data loss

   https://doi.org/10.1117/12.2633172  

   Marquard, Dillon; Wright, Kyle; Marcia, Roummel F. (October 2022, SPIE Optical Engineering + Applications, 2022)

   Zelinski, Michael E.; Taha, Tarek M.; Howe, Jonathan (Ed.)

   Image classification forms an important class of problems in machine learning and is widely used in many realworld applications, such as medicine, ecology, astronomy, and defense. Convolutional neural networks (CNNs) are machine learning techniques designed for inputs with grid structures, e.g., images, whose features are spatially correlated. As such, CNNs have been demonstrated to be highly effective approaches for many image classification problems and have consistently outperformed other approaches in many image classification and object detection competitions. A particular challenge involved in using machine learning for classifying images is measurement data loss in the form of missing pixels, which occurs in settings where scene occlusions are present or where the photodetectors in the imaging system are partially damaged. In such cases, the performance of CNN models tends to deteriorate or becomes unreliable even when the perturbations to the input image are small. In this work, we investigate techniques for improving the performance of CNN models for image classification with missing data. In particular, we explore training on a variety of data alterations that mimic data loss for producing more robust classifiers. By optimizing the categorical cross-entropy loss function, we demonstrate through numerical experiments on the MNIST dataset that training with these synthetic alterations can enhance the classification accuracy of our CNN models. 

   more » « less
3. EGIS: Entropy Guided Image Synthesis for Dataset-Agnostic Testing of RRAM-Based DNNs

   Saha, A; Amarnath, C; Ma, K; Chatterjee, A (March 2025, IEEE)

   While resistive random access memory (RRAM) based deep neural networks (DNN) are important for low-power inference in IoT and edge applications, they are vulnerable to the effects of manufacturing process variations that degrade their performance (classification accuracy). However, to test the same post-manufacture, the (image) dataset used to train the associated machine learning applications may not be available to the RRAM crossbar manufacturer for privacy reasons. As such, the performance of DNNs needs to be assessed with carefully crafted dataset-agnostic synthetic test images that expose anomalies in the crossbar manufacturing process to the maximum extent possible. In this work, we propose a dataset-agnostic post-manufacture testing framework for RRAM-based DNNs using Entropy Guided Image Synthesis (EGIS). We first create a synthetic image dataset such that the DNN outputs corresponding to the synthetic images minimize an entropy-based loss metric. Next, a small subset (consisting of 10-20 images) of the synthetic image dataset, called the compact image dataset, is created to expedite testing. The response of the device under test (DUT) to the compact image dataset is passed to a machine learning based outlier detector for pass/fail labeling of the DUT. It is seen that the test accuracy using such synthetic test images is very close to that of contemporary test methods. 

   more » « less
4. Single-Shot Domain Adaptation via Target-Aware Generative Augmentations

   https://doi.org/10.1109/ICASSP49357.2023.10096784  

   Subramanyam, Rakshith; Thopalli, Kowshik; Berman, Spring; Turaga, Pavan; Thiagarajan, Jayaraman J. (June 2023, ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP))

   The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks. While several test-time adaptation techniques have emerged, they typically rely on synthetic data augmentations in cases of limited target data availability. In this paper, we consider the challenging setting of single-shot adaptation and explore the design of augmentation strategies. We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA (Single-Shot Target Augmentations), which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data. Using experiments with a state-of-the-art domain adaptation method, we find that SiSTA produces improvements as high as 20% over existing baselines under challenging shifts in face attribute detection, and that it performs competitively to oracle models obtained by training on a larger target dataset. Our codes can be accessed at github.com/kowshikthopalli/SISTA. 

   more » « less
5. Generation of synthetic multi‐resolution time series load data

   https://doi.org/10.1049/stg2.12116  

   Pinceti, Andrea; Sankar, Lalitha; Kosut, Oliver (June 2023, IET Smart Grid)

   Abstract The availability of large datasets is crucial for the development of new power system applications and tools; unfortunately, very few are publicly and freely available. The authors designed an end‐to‐end generative framework for the creation of synthetic bus‐level time‐series load data for transmission networks. The model is trained on a real dataset of over 70 Terabytes of synchrophasor measurements spanning multiple years. Leveraging a combination of principal component analysis and conditional generative adversarial network models, the developed scheme allows for the generation of data at varying sampling rates (up to a maximum of 30 samples per second) and ranging in length from seconds to years. The generative models are tested extensively to verify that they correctly capture the diverse characteristics of real loads. Finally, an opensource tool called LoadGAN is developed which gives researchers access to the fully trained generative models via a graphical interface. 

   more » « less