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 • 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.
2 code implementations • NeurIPS 2023 • Yonglong Tian, Lijie Fan, Phillip Isola, Huiwen Chang, Dilip Krishnan
We investigate the potential of learning visual representations using synthetic images generated by text-to-image models.
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 • CVPR 2023 • Mingyu Ding, Yikang Shen, Lijie Fan, Zhenfang Chen, Zitian Chen, Ping Luo, Joshua B. Tenenbaum, Chuang Gan
When looking at an image, we can decompose the scene into entities and their parts as well as obtain the dependencies between them.
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 • 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)
2 code implementations • NeurIPS 2021 • Lijie Fan, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang, Chuang Gan
We show that AdvCL is able to enhance cross-task robustness transferability without loss of model accuracy and finetuning efficiency.
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.
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 • 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
no code implementations • 9 Aug 2018 • Lijie Fan, Wenbing Huang, Chuang Gan, Junzhou Huang, Boqing Gong
The recent advances in deep learning have made it possible to generate photo-realistic images by using neural networks and even to extrapolate video frames from an input video clip.
1 code implementation • CVPR 2018 • Lijie Fan, Wenbing Huang, Chuang Gan, Stefano Ermon, Boqing Gong, Junzhou Huang
Despite the recent success of end-to-end learned representations, hand-crafted optical flow features are still widely used in video analysis tasks.
Ranked #42 on Action Recognition on UCF101
no code implementations • NeurIPS 2017 • Wenbing Huang, Mehrtash Harandi, Tong Zhang, Lijie Fan, Fuchun Sun, Junzhou Huang
Linear Dynamical Systems (LDSs) are fundamental tools for modeling spatio-temporal data in various disciplines.
no code implementations • 3 Apr 2017 • Lijie Fan, Yunjie Ke
Our experiment adapts several popular deep learning methods as well as some traditional methods on the problem of video emotion recognition.