Zobrazeno 1 - 10
of 162
pro vyhledávání: '"Iyer, Rishabh"'
3D object detection is fundamentally important for various emerging applications, including autonomous driving and robotics. A key requirement for training an accurate 3D object detector is the availability of a large amount of LiDAR-based point clou
Externí odkaz:
http://arxiv.org/abs/2410.03918
Publikováno v:
Advances in Neural Information Processing Systems, 36 (2024)
Existing subset selection methods for efficient learning predominantly employ discrete combinatorial and model-specific approaches which lack generalizability. For an unseen architecture, one cannot use the subset chosen for a different model. To tac
Externí odkaz:
http://arxiv.org/abs/2409.12255
Confusion and forgetting of object classes have been challenges of prime interest in Few-Shot Object Detection (FSOD). To overcome these pitfalls in metric learning based FSOD techniques, we introduce a novel Submodular Mutual Information Learning (S
Externí odkaz:
http://arxiv.org/abs/2407.02665
As supervised fine-tuning of pre-trained models within NLP applications increases in popularity, larger corpora of annotated data are required, especially with increasing parameter counts in large language models. Active learning, which attempts to m
Externí odkaz:
http://arxiv.org/abs/2402.13468
With increasing volume of data being used across machine learning tasks, the capability to target specific subsets of data becomes more important. To aid in this capability, the recently proposed Submodular Mutual Information (SMI) has been effective
Externí odkaz:
http://arxiv.org/abs/2402.13454
In this paper we introduce the SCoRe (Submodular Combinatorial Representation Learning) framework, a novel approach in representation learning that addresses inter-class bias and intra-class variance. SCoRe provides a new combinatorial viewpoint to r
Externí odkaz:
http://arxiv.org/abs/2310.00165
Active Learning (AL) is a human-in-the-loop framework to interactively and adaptively label data instances, thereby enabling significant gains in model performance compared to random sampling. AL approaches function by selecting the hardest instances
Externí odkaz:
http://arxiv.org/abs/2306.01277
Deep neural networks have consistently shown great performance in several real-world use cases like autonomous vehicles, satellite imaging, etc., effectively leveraging large corpora of labeled training data. However, learning unbiased models depends
Externí odkaz:
http://arxiv.org/abs/2305.10643
Autor:
Renduchintala, H S V N S Kowndinya, Killamsetty, Krishnateja, Bhatia, Sumit, Aggarwal, Milan, Ramakrishnan, Ganesh, Iyer, Rishabh, Krishnamurthy, Balaji
A salient characteristic of pre-trained language models (PTLMs) is a remarkable improvement in their generalization capability and emergence of new capabilities with increasing model capacity and pre-training dataset size. Consequently, we are witnes
Externí odkaz:
http://arxiv.org/abs/2305.06677
Autor:
Killamsetty, Krishnateja, Evfimievski, Alexandre V., Pedapati, Tejaswini, Kate, Kiran, Popa, Lucian, Iyer, Rishabh
Training deep networks and tuning hyperparameters on large datasets is computationally intensive. One of the primary research directions for efficient training is to reduce training costs by selecting well-generalizable subsets of training data. Comp
Externí odkaz:
http://arxiv.org/abs/2301.13287