1 code implementation • 26 Jun 2021 • Pulkit Tandon, Shubham Chandak, Pat Pataranutaporn, Yimeng Liu, Anesu M. Mapuranga, Pattie Maes, Tsachy Weissman, Misha Sra
Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure.
1 code implementation • ICML Workshop URL 2021 • Mina Khan, P Srivatsa, Advait Rane, Shriram Chenniappa, Rishabh Anand, Sherjil Ozair, Pattie Maes
Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets.
no code implementations • 2 Jun 2021 • Mina Khan, P Srivatsa, Advait Rane, Shriram Chenniappa, Asadali Hazariwala, Pattie Maes
Self-supervised or weakly supervised models trained on large-scale datasets have shown sample-efficient transfer to diverse datasets in few-shot settings.
no code implementations • 22 May 2021 • Mina Khan, Pattie Maes
We created a wearable system, called PAL, for wearable, personalized, and privacy-preserving egocentric visual context detection.
1 code implementation • 21 Apr 2021 • Utkarsh Sarawgi, Rishab Khincha, Wazeer Zulfikar, Satrajit Ghosh, Pattie Maes
Reliability of machine learning (ML) systems is crucial in safety-critical applications such as healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of ML systems in deployment.
1 code implementation • 19 Nov 2020 • Rishab Khincha, Utkarsh Sarawgi, Wazeer Zulfikar, Pattie Maes
In this work, we propose a simple yet effective approach that clusters similar input features together using hierarchical clustering and then trains proportionately split neural networks with a joint loss.
1 code implementation • 3 Oct 2020 • Utkarsh Sarawgi, Wazeer Zulfikar, Rishab Khincha, Pattie Maes
Reliability in Neural Networks (NNs) is crucial in safety-critical applications like healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of NNs in deployment.
1 code implementation • 25 Sep 2020 • Utkarsh Sarawgi, Wazeer Zulfikar, Rishab Khincha, Pattie Maes
Our work further demonstrates its applicability in a multi-modal setting using a benchmark Alzheimer's dataset and also shows how deep split ensembles can highlight hidden modality-specific biases.
1 code implementation • 30 Aug 2020 • Utkarsh Sarawgi, Wazeer Zulfikar, Nouran Soliman, Pattie Maes
Our system achieves state-of-the-art test accuracy, precision, recall, and F1-score of 83. 3% each for AD classification, and state-of-the-art test root mean squared error (RMSE) of 4. 60 for MMSE score regression.
2 code implementations • 25 Nov 2018 • Abhay Koushik, Judith Amores, Pattie Maes
We present the first real-time sleep staging system that uses deep learning without the need for servers in a smartphone application for a wearable EEG.