PMPuneet Mangla

Puneet Mangla

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Puneet Mangla has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • On Saliency Maps and Adversarial Robustness

    by Puneet Mangla, Vedant Singh, Vineeth N. Balasubramanian


  • Open Access

    Charting the Right Manifold: Manifold Mixup for Few-shot Learning

    by Puneet Mangla, Mayank Singh, Abhishek Sinha, Nupur Kumari, Vineeth N Balasubramanian, Balaji Krishnamurthy

    Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution. Since the goal of few-shot learning is closely linked to robust representation learning, we study Manifold Mixup in this problem setting. Self-supervised learning is another technique that learns semantically meaningful features, using only the inherent structure of the data. This work investigates the role of learning relevant feature manifold for few-shot tasks using self-supervision and regularization techniques. We observe that regularizing the feature manifold, enriched via self-supervised techniques, with Manifold Mixup significantly improves few-shot learning performance. We show that our proposed method S2M2 beats the current state-of-the-art accuracy on standard few-shot learning datasets like CIFAR-FS, CUB, mini-ImageNet and tiered-ImageNet by 3-8 %. Through extensive experimentation, we show that the features learned using our approach generalize to complex few-shot evaluation tasks, cross-domain scenarios and are robust against slight changes to data distribution.

  • Open Access

    AdvGAN++ : Harnessing latent layers for adversary generation

    by Puneet Mangla, Surgan Jandial, Sakshi Varshney, Vineeth N Balasubramanian

    Adversarial examples are fabricated examples, indistinguishable from the original image that mislead neural networks and drastically lower their performance. Recently proposed AdvGAN, a GAN based approach, takes input image as a prior for generating adversaries to target a model. In this work, we show how latent features can serve as better priors than input images for adversary generation by proposing AdvGAN++, a version of AdvGAN that achieves higher attack rates than AdvGAN and at the same time generates perceptually realistic images on MNIST and CIFAR-10 datasets.