News

• [08/2024] Video: Deep Double Descent: Where Bigger Models and More Data Hurt
• [03/2024] Article: Sigmoid Loss for Language Image Pre-Training
• [01/2024] Article: The Equations Behind DALL-E
• [10/2023] Press: MICCAI 2023 Magazine has featured our M&M Paper for lesions detection in mammograms.
• [08/2023] Paper: One Paper accepted in MICCAI 2023
• [08/2023] Video: How Fully Sharded Data Parallel (FSDP) works?
• [07/2023] Article: Big Transfer (BiT): General Visual Representation Learning
• [06/2023] Article: FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
• [05/2023] Article: High Resolution Images and Efficient Transformers
• [03/2023] Article: Masked Autoencoders Are Scalable Vision Learners
• [03/2023] Milestone: I am glad to rejoin WhiteRabbit's research team as a research scientist.
• [03/2023] Milestone: My journey at Amazon has reached its ends.
• [02/2023] Article: Rethinking Attention with Performers - Part II & Final
• [10/2022] Article: Rethinking Attention with Performers - Part I
• [10/2022] Milestone: I am an Applied Scientist at Amazon.
• [09/2022] Milestone: My journey at WhiteRabbit.AI has reached its end. I have been lucky to work with WhiteRabbit's research team and Nhi (a.k.a. Yen Nhi). Nhi is one of my best colleagues/co-authors.
• [08/2022] Paper: One Paper accepted in MICCAI 2022
• [07/2022] Github: Official PyTorch implementation of Deep is a Luxury We Don't Have
• [05/2022] Article: Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
• [04/2022] Article: Understanding Transfer Learning for Medical Imaging
• [01/2022] Article: Sharpness-Aware Minimization for Efficiently Improving Generalization
• [12/2021] Article: Feature Embedding Regularizers: SVMax & VICReg
• [11/2021] Article: IIRC: Incremental Implicitly-Refined Classification
• [08/2021] Article: Knowledge Evolution in Neural Networks
• [07/2021] Article: Cross-Iteration Batch Normalization
• [07/2021] Milestone: I am a research scientist at WhiteRabbit.AI
• [05/2021] Milestone: My journey at the University of Maryland has reached its end; I received a Ph.D. degree in Computer Vision. I have been lucky to have both Prof Larry Davis and Abhinav Shrivastava as my Ph.D. supervisors.
• [05/2021] Article: L2-CAF: A Neural Network Debugger
• [04/2021] Article: Deep Metric Learning Beyond Binary Supervision
• [03/2021] Defended my PhD dissertation 💪 🎉🎉
• [03/2021] Paper: One Oral Paper accepted in CVPR 2021
• [01/2021] Article: Energy and Policy Considerations for Deep Learning in NLP
• [01/2021] Github: PyTorch implementation of Exploring Simple Siamese Representation Learning
• [12/2020] Article: Mining on Manifolds: Metric Learning without Labels
• [12/2020] Github: Tensorflow implementation of Representation Learning by Learning to Count
• [09/2020] Article: A Generic Visualization Approach for Convolutional Neural Networks
• [08/2020] Article: Proxy Anchor Loss for Deep Metric Learning
• [08/2020] Article: Why Does Unsupervised Pre-training Help Deep Learning?
• [07/2020] Paper: One Paper accepted in ECCV 2020
• [03/2020] Article: Boosting Standard Classification Architectures Through a Ranking Regularizer
• [12/2019] Paper: One Paper accepted in WACV 2020
• [11/2019] Article: Deep Image Prior
• [09/2019] Article: Distilling the Knowledge in a Neural Network
• [06/2019] Github: A Tensorflow baseline image retrieval baseline
• [12/2018] Article: Yet Another Imbalance Data Handling Approach
• [11/2018] Article: Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• [09/2018] Github: Fine-Grained Visual Recognition Tensorflow baseline implementation
• [09/2018] Two Papers accepted in MICCAI 2018
• [08/2018] Article: Bilinear CNN Models for Fine-grained Visual Recognition
• [06/2018] Workshop Paper: Two Stream Self-Supervised Learning for Action Recognition
• [09/2015] Paper: Seeded Laplacian: An interactive image segmentation approach using eigenfunctions