Search Results for author:
Found 10 papers, 5 papers with code
Teaching CNNs to mimic Human Visual Cognitive Process & regularise Texture-Shape bias
Recent experiments in computer vision demonstrate texture bias as the primary reason for supreme results in models employing Convolutional Neural Networks (CNNs), conflicting with early works claiming that these networks identify objects using shape.
What if Neural Networks had SVDs?
We present an algorithm that is fast enough to speed up several matrix operations.
Rule Augmented Unsupervised Constituency Parsing
We introduce a novel formulation that takes advantage of the syntactic grammar rules and is independent of the base system.
MIMOQA: Multimodal Input Multimodal Output Question Answering
In this paper, we propose a novel task - MIMOQA - Multimodal Input Multimodal Output Question Answering in which the output is also multimodal.
Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time
In several real world applications, machine learning models are deployed to make predictions on data whose distribution changes gradually along time, leading to a drift between the train and test distributions.
DAFT: Distilling Adversarially Fine-tuned Models for Better OOD Generalization
We consider the problem of OOD generalization, where the goal is to train a model that performs well on test distributions that are different from the training distribution.
Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks
To bridge the gap between these two lines of work, we first hypothesize and verify that while SB may not altogether preclude learning complex features, it amplifies simpler features over complex ones.
End-to-End Neural Network Compression via $\frac{\ell_1}{\ell_2}$ Regularized Latency Surrogates
Our algorithm is versatile and can be used with many popular compression methods including pruning, low-rank factorization, and quantization.
Label Differential Privacy via Aggregation
Further, the $\ell_2^2$-regressor which minimizes the loss on the aggregated dataset has a loss within $\left(1 + o(1)\right)$-factor of the optimum on the original dataset w. p.
PEEKABOO: Interactive Video Generation via Masked-Diffusion
Recently there has been a lot of progress in text-to-video generation, with state-of-the-art models being capable of generating high quality, realistic videos.
