Zobrazeno 1 - 10
of 253
pro vyhledávání: '"Sarkar, Anindya"'
Autor:
Sarkar, Anindya, Sastry, Srikumar, Pirinen, Aleksis, Zhang, Chongjie, Jacobs, Nathan, Vorobeychik, Yevgeniy
We consider the task of active geo-localization (AGL) in which an agent uses a sequence of visual cues observed during aerial navigation to find a target specified through multiple possible modalities. This could emulate a UAV involved in a search-an
Externí odkaz:
http://arxiv.org/abs/2406.01917
Active search formalizes a specialized active learning setting where the goal is to collect members of a rare, valuable class. The state-of-the-art algorithm approximates the optimal Bayesian policy in a budget-aware manner, and has been shown to ach
Externí odkaz:
http://arxiv.org/abs/2405.15031
Graphs are commonly used to model complex networks prevalent in modern social media and literacy applications. Our research investigates the vulnerability of these graphs through the application of feature based adversarial attacks, focusing on both
Externí odkaz:
http://arxiv.org/abs/2402.12426
Visual active search (VAS) has been proposed as a modeling framework in which visual cues are used to guide exploration, with the goal of identifying regions of interest in a large geospatial area. Its potential applications include identifying hot s
Externí odkaz:
http://arxiv.org/abs/2310.09689
Autor:
Sarkar, Anindya, Lanier, Michael, Alfeld, Scott, Feng, Jiarui, Garnett, Roman, Jacobs, Nathan, Vorobeychik, Yevgeniy
Many problems can be viewed as forms of geospatial search aided by aerial imagery, with examples ranging from detecting poaching activity to human trafficking. We model this class of problems in a visual active search (VAS) framework, which has three
Externí odkaz:
http://arxiv.org/abs/2211.15788
Most reinforcement learning algorithms implicitly assume strong synchrony. We present novel attacks targeting Q-learning that exploit a vulnerability entailed by this assumption by delaying the reward signal for a limited time period. We consider two
Externí odkaz:
http://arxiv.org/abs/2209.03540
The most popular design paradigm for Graph Neural Networks (GNNs) is 1-hop message passing -- aggregating information from 1-hop neighbors repeatedly. However, the expressive power of 1-hop message passing is bounded by the Weisfeiler-Lehman (1-WL) t
Externí odkaz:
http://arxiv.org/abs/2205.13328
Autor:
Samanta, Arpita, Bera, Melinda Kumar, Bera, Subir, Longstaffe, Fred J., Paul, Shubhabrata, Kumar, Kishor, Sarkar, Anindya
Publikováno v:
In Global and Planetary Change December 2024 243
Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ only by some regularizers either at inner maximization or outer minimization steps. Being repetitive in nature during the inner maximization step, they
Externí odkaz:
http://arxiv.org/abs/2111.00295
Self-explaining deep models are designed to learn the latent concept-based explanations implicitly during training, which eliminates the requirement of any post-hoc explanation generation technique. In this work, we propose one such model that append
Externí odkaz:
http://arxiv.org/abs/2108.11761