1 code implementation • 26 May 2022 • Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, KaiFeng Chen, Sham Kakade, Prateek Jain, Ali Farhadi
The flexibility within the learned Matryoshka Representations offer: (a) up to 14x smaller embedding size for ImageNet-1K classification at the same level of accuracy; (b) up to 14x real-world speed-ups for large-scale retrieval on ImageNet-1K and 4K; and (c) up to 2% accuracy improvements for long-tail few-shot classification, all while being as robust as the original representations.
Ranked #20 on Image Classification on ObjectNet (using extra training data)
Recent advances have enabled automatic sound recognition systems for deaf and hard of hearing (DHH) users on mobile devices.
Given a video, we replace snippets of text and audio with a MASK token; the model learns by choosing the correct masked-out snippet.
Ranked #1 on Action Classification on Kinetics-600 (using extra training data)
When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes.
We further quantitatively measure the quality of our codes by applying it to the efficient image retrieval as well as out-of-distribution (OOD) detection problems.
To foster research towards the goal of general ML methods, we introduce a new unified evaluation framework - FLUID (Flexible Sequential Data).
Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps.
Ranked #13 on Face Detection on WIDER Face (Medium)
Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget.
Edge sensing with micro-power pulse-Doppler radars is an emergent domain in monitoring and surveillance with several smart city applications.
FastRNN addresses these limitations by adding a residual connection that does not constrain the range of the singular values explicitly and has only two extra scalar parameters.