no code implementations • SemEval (NAACL) 2022 • Tanuj Shekhawat, Manoj Kumar, Udaybhan Rathore, Aditya Joshi, Jasabanta Patro
This paper describes the system architectures and the models submitted by our team “IISERB Brains” to SemEval 2022 Task 6 competition.
no code implementations • NAACL (ACL) 2022 • Manoj Kumar, Yuval Merhav, Haidar Khan, Rahul Gupta, Anna Rumshisky, Wael Hamza
Use of synthetic data is rapidly emerging as a realistic alternative to manually annotating live traffic for industry-scale model building.
no code implementations • 15 Mar 2024 • Andreas Bär, Neil Houlsby, Mostafa Dehghani, Manoj Kumar
Training a linear classifier or lightweight model on top of pretrained vision model outputs, so-called 'frozen features', leads to impressive performance on a number of downstream few-shot tasks.
1 code implementation • NeurIPS 2023 • Michael Tschannen, Manoj Kumar, Andreas Steiner, Xiaohua Zhai, Neil Houlsby, Lucas Beyer
We further analyze the effect of the model architecture and scale, as well as the pretraining data on the representation quality, and find that captioning exhibits the same or better scaling behavior along these axes.
1 code implementation • 10 Feb 2023 • Mostafa Dehghani, Josip Djolonga, Basil Mustafa, Piotr Padlewski, Jonathan Heek, Justin Gilmer, Andreas Steiner, Mathilde Caron, Robert Geirhos, Ibrahim Alabdulmohsin, Rodolphe Jenatton, Lucas Beyer, Michael Tschannen, Anurag Arnab, Xiao Wang, Carlos Riquelme, Matthias Minderer, Joan Puigcerver, Utku Evci, Manoj Kumar, Sjoerd van Steenkiste, Gamaleldin F. Elsayed, Aravindh Mahendran, Fisher Yu, Avital Oliver, Fantine Huot, Jasmijn Bastings, Mark Patrick Collier, Alexey Gritsenko, Vighnesh Birodkar, Cristina Vasconcelos, Yi Tay, Thomas Mensink, Alexander Kolesnikov, Filip Pavetić, Dustin Tran, Thomas Kipf, Mario Lučić, Xiaohua Zhai, Daniel Keysers, Jeremiah Harmsen, Neil Houlsby
The scaling of Transformers has driven breakthrough capabilities for language models.
Ranked #1 on Zero-Shot Transfer Image Classification on ObjectNet
7 code implementations • 2 Feb 2023 • Manoj Kumar, Mostafa Dehghani, Neil Houlsby
We propose Dual PatchNorm: two Layer Normalization layers (LayerNorms), before and after the patch embedding layer in Vision Transformers.
no code implementations • 24 Jan 2023 • Sebastian Michelmann, Manoj Kumar, Kenneth A. Norman, Mariya Toneva
In the future, GPT-3 may thereby help to elucidate the principles underlying human event perception.
no code implementations • 2 Oct 2022 • Manoj Kumar, Anurag Sharma, Sandeep Kumar
In this paper, we introduce a novel optimization-based framework for graph dimensionality reduction.
no code implementations • 25 Jun 2022 • Yining Lu, Changjie Lu, Naina Bandyopadhyay, Manoj Kumar, Gaurav Gupta
In order to evaluate the proposed RTB strategy's performance, we demonstrate the results on ten sequential simulated auction campaigns.
no code implementations • 9 Mar 2022 • Manoj Kumar, Neil Houlsby, Nal Kalchbrenner, Ekin D. Cubuk
Perceptual distances between images, as measured in the space of pre-trained deep features, have outperformed prior low-level, pixel-based metrics on assessing perceptual similarity.
1 code implementation • 4 Mar 2022 • Tanuj Singh Shekhawat, Manoj Kumar, Udaybhan Rathore, Aditya Joshi, Jasabanta Patro
This paper describes the system architectures and the models submitted by our team "IISERBBrains" to SemEval 2022 Task 6 competition.
2 code implementations • 14 Nov 2021 • Lasse Espeholt, Shreya Agrawal, Casper Sønderby, Manoj Kumar, Jonathan Heek, Carla Bromberg, Cenk Gazen, Jason Hickey, Aaron Bell, Nal Kalchbrenner
An emerging class of weather models based on neural networks represents a paradigm shift in weather forecasting: the models learn the required transformations from data instead of relying on hand-coded physics and are computationally efficient.
no code implementations • 16 Feb 2021 • Federico Corberi, Alessandro Iannone, Manoj Kumar, Eugenio Lippiello, Paolo Politi
We study the kinetics after a low temperature quench of the one-dimensional Ising model with long range interactions between spins at distance $r$ decaying as $r^{-\alpha}$.
Statistical Mechanics
2 code implementations • ICLR 2021 • Manoj Kumar, Dirk Weissenborn, Nal Kalchbrenner
We present the Colorization Transformer, a novel approach for diverse high fidelity image colorization based on self-attention.
Ranked #2 on Colorization on ImageNet val
no code implementations • 28 Jan 2021 • Manoj Kumar, Varun Kumar, Hadrien Glaude, Cyprien delichy, Aman Alok, Rahul Gupta
We make use of a conditional generator for data augmentation that is trained directly using the meta-learning objective and simultaneously with prototypical networks, hence ensuring that data augmentation is customized to the task.
no code implementations • 13 Jan 2021 • Manoj Kumar
Which leads to the necessary and sufficient condition for satisfiability of a boolean formula, in CNF.
Computational Complexity
1 code implementation • 31 Jul 2020 • Manoj Kumar, Tae Jin-Park, Somer Bishop, Shrikanth Narayanan
Our experiments illustrate the applicability of meta-learning as a generalized learning paradigm for training deep neural speaker embeddings.
Audio and Speech Processing Sound
1 code implementation • 5 Mar 2020 • Tae Jin Park, Kyu J. Han, Manoj Kumar, Shrikanth Narayanan
In this study, we propose a new spectral clustering framework that can auto-tune the parameters of the clustering algorithm in the context of speaker diarization.
Ranked #1 on Speaker Diarization on CALLHOME (DER(ig olp) metric)
no code implementations • 25 Oct 2019 • Rimita Lahiri, Manoj Kumar, Somer Bishop, Shrikanth Narayanan
Diagnostic procedures for ASD (autism spectrum disorder) involve semi-naturalistic interactions between the child and a clinician.
1 code implementation • ICLR 2020 • Manoj Kumar, Mohammad Babaeizadeh, Dumitru Erhan, Chelsea Finn, Sergey Levine, Laurent Dinh, Durk Kingma
Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions.
Ranked #15 on Video Generation on BAIR Robot Pushing
no code implementations • 8 Jun 2018 • Victor Ardulov, Manoj Kumar, Shanna Williams, Thomas Lyon, Shrikanth Narayanan
Child Forensic Interviewing (FI) presents a challenge for effective information retrieval and decision making.
1 code implementation • 25 May 2018 • Manoj Kumar, George E. Dahl, Vijay Vasudevan, Mohammad Norouzi
We present a simple and powerful algorithm for parallel black box optimization called Successive Halving and Classification (SHAC).
no code implementations • 9 Aug 2017 • Jeremy Kepner, Manoj Kumar, José Moreira, Pratap Pattnaik, Mauricio Serrano, Henry Tufo
The performance of the GraphBLAS implementation is measured relative to a standard dense linear algebra library implementation.