Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Vedantam, Ramakrishna"'
Autor:
Wang, Kai, Li, Zekai, Cheng, Zhi-Qi, Khaki, Samir, Sajedi, Ahmad, Vedantam, Ramakrishna, Plataniotis, Konstantinos N, Hauptmann, Alexander, You, Yang
Dataset distillation has demonstrated strong performance on simple datasets like CIFAR, MNIST, and TinyImageNet but struggles to achieve similar results in more complex scenarios. In this paper, we propose EDF (emphasizes the discriminative features)
Externí odkaz:
http://arxiv.org/abs/2410.17193
Autor:
Kirichenko, Polina, Ibrahim, Mark, Balestriero, Randall, Bouchacourt, Diane, Vedantam, Ramakrishna, Firooz, Hamed, Wilson, Andrew Gordon
Data augmentation (DA) encodes invariance and provides implicit regularization critical to a model's performance in image classification tasks. However, while DA improves average accuracy, recent studies have shown that its impact can be highly class
Externí odkaz:
http://arxiv.org/abs/2401.01764
Dataset distillation extracts a small set of synthetic training samples from a large dataset with the goal of achieving competitive performance on test data when trained on this sample. In this work, we tackle dataset distillation at its core by trea
Externí odkaz:
http://arxiv.org/abs/2311.07025
Autor:
Dancette, Corentin, Whitehead, Spencer, Maheshwary, Rishabh, Vedantam, Ramakrishna, Scherer, Stefan, Chen, Xinlei, Cord, Matthieu, Rohrbach, Marcus
Despite advances in Visual Question Answering (VQA), the ability of models to assess their own correctness remains underexplored. Recent work has shown that VQA models, out-of-the-box, can have difficulties abstaining from answering when they are wro
Externí odkaz:
http://arxiv.org/abs/2306.08751
Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept "dog" entails all images that contain dogs. Despite being intuitive, current large-scale vision and language models such as CLIP do not explicitly ca
Externí odkaz:
http://arxiv.org/abs/2304.09172
Humans can learn and reason under substantial uncertainty in a space of infinitely many concepts, including structured relational concepts ("a scene with objects that have the same color") and ad-hoc categories defined through goals ("objects that co
Externí odkaz:
http://arxiv.org/abs/2010.02855
We address the question of characterizing and finding optimal representations for supervised learning. Traditionally, this question has been tackled using the Information Bottleneck, which compresses the inputs while retaining information about the t
Externí odkaz:
http://arxiv.org/abs/2009.12789
Autor:
Modhe, Nirbhay, Chattopadhyay, Prithvijit, Sharma, Mohit, Das, Abhishek, Parikh, Devi, Batra, Dhruv, Vedantam, Ramakrishna
We propose a novel framework to identify sub-goals useful for exploration in sequential decision making tasks under partial observability. We utilize the variational intrinsic control framework (Gregor et.al., 2016) which maximizes empowerment -- the
Externí odkaz:
http://arxiv.org/abs/1907.10580
Autor:
Vedantam, Ramakrishna, Desai, Karan, Lee, Stefan, Rohrbach, Marcus, Batra, Dhruv, Parikh, Devi
We propose a new class of probabilistic neural-symbolic models, that have symbolic functional programs as a latent, stochastic variable. Instantiated in the context of visual question answering, our probabilistic formulation offers two key conceptual
Externí odkaz:
http://arxiv.org/abs/1902.07864
It is easy for people to imagine what a man with pink hair looks like, even if they have never seen such a person before. We call the ability to create images of novel semantic concepts visually grounded imagination. In this paper, we show how we can
Externí odkaz:
http://arxiv.org/abs/1705.10762