1 code implementation • 28 Dec 2023 • Yonglong Tian, Lijie Fan, KaiFeng Chen, Dina Katabi, Dilip Krishnan, Phillip Isola
We introduce SynCLR, a novel approach for learning visual representations exclusively from synthetic images and synthetic captions, without any real data.
1 code implementation • 11 Dec 2023 • Yuzhe Yang, Haoran Zhang, Judy W Gichoya, Dina Katabi, Marzyeh Ghassemi
As artificial intelligence (AI) rapidly approaches human-level performance in medical imaging, it is crucial that it does not exacerbate or propagate healthcare disparities.
1 code implementation • 7 Dec 2023 • Lijie Fan, KaiFeng Chen, Dilip Krishnan, Dina Katabi, Phillip Isola, Yonglong Tian
Our findings also suggest that scaling synthetic data can be particularly effective in scenarios such as: (1) when there is a limited supply of real images for a supervised problem (e. g., fewer than 0. 5 million images in ImageNet), (2) when the evaluation dataset diverges significantly from the training data, indicating the out-of-distribution scenario, or (3) when synthetic data is used in conjunction with real images, as demonstrated in the training of CLIP models.
1 code implementation • 6 Dec 2023 • Tianhong Li, Dina Katabi, Kaiming He
This gap can be attributed to the lack of semantic information provided by labels.
Ranked #1 on Unconditional Image Generation on ImageNet 256x256
no code implementations • 5 Oct 2023 • Tianhong Li, Sangnie Bhardwaj, Yonglong Tian, Han Zhang, Jarred Barber, Dina Katabi, Guillaume Lajoie, Huiwen Chang, Dilip Krishnan
We demonstrate image generation and captioning performance on par with state-of-the-art text-to-image and image-to-text models with orders of magnitude fewer (only 3M) paired image-text data.
1 code implementation • ICCV 2023 • Yeonghwan Song, Seokwoo Jang, Dina Katabi, Jeany Son
We propose a novel unsupervised object localization method that allows us to explain the predictions of the model by utilizing self-supervised pre-trained models without additional finetuning.
1 code implementation • NeurIPS 2023 • Lijie Fan, Dilip Krishnan, Phillip Isola, Dina Katabi, Yonglong Tian
During training, LaCLIP randomly selects either the original texts or the rewritten versions as text augmentations for each image.
no code implementations • 23 May 2023 • Tianhong Li, Vibhaalakshmi Sivaraman, Pantea Karimi, Lijie Fan, Mohammad Alizadeh, Dina Katabi
Packet loss during video conferencing often leads to poor quality and video freezing.
1 code implementation • 23 Feb 2023 • Yuzhe Yang, Haoran Zhang, Dina Katabi, Marzyeh Ghassemi
Machine learning models often perform poorly on subgroups that are underrepresented in the training data.
no code implementations • 6 Dec 2022 • Hao He, Yuan Yuan, Ying-Cong Chen, Peng Cao, Dina Katabi
With the increasing popularity of telehealth, it becomes critical to ensure that basic physiological signals can be monitored accurately at home, with minimal patient overhead.
1 code implementation • CVPR 2023 • Tianhong Li, Huiwen Chang, Shlok Kumar Mishra, Han Zhang, Dina Katabi, Dilip Krishnan
In this work, we propose MAsked Generative Encoder (MAGE), the first framework to unify SOTA image generation and self-supervised representation learning.
Ranked #2 on Unconditional Image Generation on ImageNet 256x256
1 code implementation • 6 Oct 2022 • Yuzhe Yang, Xin Liu, Jiang Wu, Silviu Borac, Dina Katabi, Ming-Zher Poh, Daniel McDuff
From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes.
no code implementations • 6 Jul 2022 • Tianhong Li, Lijie Fan, Yuan Yuan, Dina Katabi
Thus, in this paper, we explore the feasibility of adapting RGB-based unsupervised representation learning to RF signals.
1 code implementation • 17 Mar 2022 • Yuzhe Yang, Hao Wang, Dina Katabi
We first develop the domain-class transferability graph, and show that such transferability governs the success of learning in MDLT.
1 code implementation • 22 Feb 2022 • Hao He, Kaiwen Zha, Dina Katabi
We propose Contrastive Poisoning (CP), the first effective such attack on CL.
1 code implementation • CVPR 2022 • Sivan Harary, Eli Schwartz, Assaf Arbelle, Peter Staar, Shady Abu-Hussein, Elad Amrani, Roei Herzig, Amit Alfassy, Raja Giryes, Hilde Kuehne, Dina Katabi, Kate Saenko, Rogerio Feris, Leonid Karlinsky
The ability to generalize learned representations across significantly different visual domains, such as between real photos, clipart, paintings, and sketches, is a fundamental capacity of the human visual system.
1 code implementation • CVPR 2022 • Tianhong Li, Peng Cao, Yuan Yuan, Lijie Fan, Yuzhe Yang, Rogerio Feris, Piotr Indyk, Dina Katabi
This forces all classes, including minority classes, to maintain a uniform distribution in the feature space, improves class boundaries, and provides better generalization even in the presence of long-tail data.
Ranked #22 on Long-tail Learning on CIFAR-10-LT (ρ=100)
1 code implementation • 18 Feb 2021 • Yuzhe Yang, Kaiwen Zha, Ying-Cong Chen, Hao Wang, Dina Katabi
We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range.
no code implementations • 1 Jan 2021 • Hao He, Ying-Cong Chen, Yuan Yuan, Dina Katabi
Further, since breathing can be monitored without body contact by analyzing the radio signal in the environment, we show that oxygen too can be monitored without any wearable devices.
no code implementations • 17 Dec 2020 • Tianhong Li, Lijie Fan, Yuan Yuan, Hao He, Yonglong Tian, Rogerio Feris, Piotr Indyk, Dina Katabi
However, contrastive learning is susceptible to feature suppression, i. e., it may discard important information relevant to the task of interest, and learn irrelevant features.
no code implementations • ECCV 2020 • Lijie Fan, Tianhong Li, Yuan Yuan, Dina Katabi
This paper aims to caption daily life --i. e., to create a textual description of people's activities and interactions with objects in their homes.
1 code implementation • ICML 2020 • Hao Wang, Hao He, Dina Katabi
Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.
Ranked #1 on Domain Adaptation on Rotating MNIST
1 code implementation • ICML 2020 • Hao Wang, Hao He, Dina Katabi
Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.
no code implementations • ICLR 2020 • Chen-Yu Hsu, Abbas Zeitoun, Guang-He Lee, Dina Katabi, Tommi Jaakkola
We show that this cross-modal prediction task allows us to detect when a particular appliance is used, and the location of the appliance in the home, all in a self-supervised manner, without any labeled data.
no code implementations • CVPR 2020 • Lijie Fan, Tianhong Li, Rongyao Fang, Rumen Hristov, Yuan Yuan, Dina Katabi
RF signals traverse clothes and reflect off the human body; thus they can be used to extract more persistent human-identifying features like body size and shape.
no code implementations • ICLR 2020 • Yunzhu Li, Hao He, Jiajun Wu, Dina Katabi, Antonio Torralba
Finding an embedding space for a linear approximation of a nonlinear dynamical system enables efficient system identification and control synthesis.
1 code implementation • ICLR 2020 • Yuzhe Yang, Guo Zhang, Zhi Xu, Dina Katabi
In this paper, we propose to exploit the underlying structures of the state-action value function, i. e., Q function, for both planning and deep RL.
no code implementations • ICCV 2019 • Tianhong Li, Lijie Fan, Ming-Min Zhao, Yingcheng Liu, Dina Katabi
Understanding people's actions and interactions typically depends on seeing them.
Ranked #1 on RF-based Pose Estimation on RF-MMD
1 code implementation • 28 May 2019 • Yuzhe Yang, Guo Zhang, Dina Katabi, Zhi Xu
We show that this process destroys the adversarial structure of the noise, while re-enforcing the global structure in the original image.
no code implementations • ICLR 2019 • Chen-Yu Hsu, Piotr Indyk, Dina Katabi, Ali Vakilian
Estimating the frequencies of elements in a data stream is a fundamental task in data analysis and machine learning.
no code implementations • 6 Feb 2019 • Hao Wang, Chengzhi Mao, Hao He, Ming-Min Zhao, Tommi S. Jaakkola, Dina Katabi
We consider the problem of inferring the values of an arbitrary set of variables (e. g., risk of diseases) given other observed variables (e. g., symptoms and diagnosed diseases) and high-dimensional signals (e. g., MRI images or EEG).
no code implementations • Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2018 • Yonglong Tian, Guang-He Lee, Hao He, Chen-Yu Hsu, Dina Katabi
Falls are the top reason for fatal and non-fatal injuries among seniors.
Ranked #2 on RF-based Pose Estimation on RF-MMD
no code implementations • SIGCOMM '18 Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication 2018 • Ming-Min Zhao, Yonglong Tian, Hang Zhao, Mohammad Abu Alsheikh, Tianhong Li, Rumen Hristov, Zachary Kabelac, Dina Katabi, Antonio Torralba
It maintains this accuracy even in the presence of multiple people, and in new environments that it has not seen in the training set.
no code implementations • CVPR 2018 • Ming-Min Zhao, Tianhong Li, Mohammad Abu Alsheikh, Yonglong Tian, Hang Zhao, Antonio Torralba, Dina Katabi
Yet, unlike vision-based pose estimation, the radio-based system can estimate 2D poses through walls despite never trained on such scenarios.
no code implementations • ICML 2017 • Ming-Min Zhao, Shichao Yue, Dina Katabi, Tommi S. Jaakkola, Matt T. Bianchi
We focus on predicting sleep stages from radio measurements without any attached sensors on subjects.