Manoj Acharya

abstract / bibtex

Humans can incrementally learn to do new visual detection tasks, which is a huge challenge for today's computer vision systems. Incrementally trained deep learning models lack backwards transfer to previously seen classes and suffer from a phenomenon known as ``catastrophic forgetting.'' In this paper, we pioneer online streaming learning for object detection, where an agent must learn examples one at a time with severe memory and computational constraints. In object detection, a system must output all bounding boxes for an image with the correct label. Unlike earlier work, the system described in this paper can learn how to do this task in an online manner with new classes being introduced over time. We achieve this capability by using a novel memory replay mechanism that replays entire scenes in an efficient manner. We achieve state-of-the-art results on both the PASCAL VOC 2007 and MS COCO datasets.

coming soon....

abstract / bibtex / code

People learn throughout life. However, incrementally updating conventional neural networks leads to catastrophic forgetting. A common remedy is replay, which is inspired by how the brain consolidates memory. Replay involves fine-tuning a network on a mixture of new and old instances. While there is neuroscientific evidence that the brain replays compressed memories, existing methods for convolutional networks replay raw images. Here, we propose REMIND, a brain-inspired approach that enables efficient replay with compressed representations. REMIND is trained in an online manner, meaning it learns one example at a time, which is closer to how humans learn. Under the same constraints, REMIND outperforms other methods for incremental class learning on the ImageNet ILSVRC-2012 dataset. We probe REMIND's robustness to data ordering schemes known to induce catastrophic forgetting. We demonstrate REMIND's generality by pioneering online learning for Visual Question Answering (VQA).

@article{hayes2019remind,
title={REMIND Your Neural Network to Prevent Catastrophic Forgetting},
author={Hayes, Tyler L and Kafle, Kushal and Shrestha, Robik and Acharya, Manoj and Kanan, Christopher},
journal={arXiv preprint arXiv:1910.02509},
year={2019}
}

abstract / bibtex / code

Accurate eye segmentation can improve eye-gaze estimation and support interactive computing based on visual attention; however, existing eye segmentation methods suffer from issues such as person-dependent accuracy, lack of robustness, and an inability to be run in real-time. Here, we present the RITnet model, which is a deep neural network that combines U-Net and DenseNet. RITnet is under 1 MB and achieves 95.3% accuracy on the 2019 OpenEDS Semantic Segmentation challenge. Using a GeForce GTX 1080 Ti, RITnet tracks at > 300Hz, enabling real-time gaze tracking applications. Pre-trained models and source code are available this https URL.

@inproceedings{chaudhary2019ritnet,
title={RITnet: real-time semantic segmentation of the eye for gaze tracking},
author={Chaudhary, Aayush K and Kothari, Rakshit and Acharya, Manoj and Dangi, Shusil and Nair, Nitinraj and Bailey, Reynold and Kanan, Christopher and Diaz, Gabriel and Pelz, Jeff B},
booktitle={2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)},
pages={3698--3702},
year={2019},
organization={IEEE}
}

abstract / bibtex / website

We propose Visual Query Detection (VQD), a new visual grounding task. In VQD, a system is guided by natural language to localize a variable number of objects in an image. VQD is related to visual referring expression recognition, where the task is to localize only one object. We describe the first dataset for VQD and we propose baseline algorithms that demonstrate the difficulty of the task compared to referring expression recognition.

@article{acharya2019vqd,
title={VQD: Visual query detection in natural scenes},
author={Acharya, Manoj and Jariwala, Karan and Kanan, Christopher},
journal={arXiv preprint arXiv:1904.02794},
year={2019}
}

abstract / bibtex / website / code

Most counting questions in visual question answering (VQA) datasets are simple and require no more than object detection. Here, we study algorithms for complex counting questions that involve relationships between objects, attribute identification, reasoning, and more. To do this, we created TallyQA, the world's largest dataset for open-ended counting. We propose a new algorithm for counting that uses relation networks with region proposals. Our method lets relation networks be efficiently used with high-resolution imagery. It yields state-of-the-art results compared to baseline and recent systems on both TallyQA and the HowMany-QA benchmark.

@inproceedings{acharya2019tallyqa,
title={TallyQA: Answering complex counting questions},
author={Acharya, Manoj and Kafle, Kushal and Kanan, Christopher},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={33},
pages={8076--8084},
year={2019}
}