Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Khanna, Samar"'
Autor:
Irvin, Jeremy Andrew, Liu, Emily Ruoyu, Chen, Joyce Chuyi, Dormoy, Ines, Kim, Jinyoung, Khanna, Samar, Zheng, Zhuo, Ermon, Stefano
Large vision and language assistants have enabled new capabilities for interpreting natural images. These approaches have recently been adapted to earth observation data, but they are only able to handle single image inputs, limiting their use for ma
Externí odkaz:
http://arxiv.org/abs/2410.06234
Parameter-efficient fine-tuning (PEFT) techniques such as low-rank adaptation (LoRA) can effectively adapt large pre-trained foundation models to downstream tasks using only a small fraction (0.1%-10%) of the original trainable weights. An under-expl
Externí odkaz:
http://arxiv.org/abs/2406.10973
Autor:
Foucard, Louis, Khanna, Samar, Shi, Yi, Liu, Chi-Kuei, Shen, Quinn Z, Ngo, Thuyen, Xia, Zi-Xiang
In this paper, we propose SpotNet: a fast, single stage, image-centric but LiDAR anchored approach for long range 3D object detection. We demonstrate that our approach to LiDAR/image sensor fusion, combined with the joint learning of 2D and 3D detect
Externí odkaz:
http://arxiv.org/abs/2405.15843
Large Language Models (LLMs) inherently carry the biases contained in their training corpora, which can lead to the perpetuation of societal harm. As the impact of these foundation models grows, understanding and evaluating their biases becomes cruci
Externí odkaz:
http://arxiv.org/abs/2402.02680
Autor:
Khanna, Samar, Liu, Patrick, Zhou, Linqi, Meng, Chenlin, Rombach, Robin, Burke, Marshall, Lobell, David, Ermon, Stefano
Diffusion models have achieved state-of-the-art results on many modalities including images, speech, and video. However, existing models are not tailored to support remote sensing data, which is widely used in important applications including environ
Externí odkaz:
http://arxiv.org/abs/2312.03606
The application of machine learning (ML) in a range of geospatial tasks is increasingly common but often relies on globally available covariates such as satellite imagery that can either be expensive or lack predictive power. Here we explore the ques
Externí odkaz:
http://arxiv.org/abs/2310.06213
Diffusion models are powerful generative models that map noise to data using stochastic processes. However, for many applications such as image editing, the model input comes from a distribution that is not random noise. As such, diffusion models mus
Externí odkaz:
http://arxiv.org/abs/2309.16948
One of the major drawbacks of deep learning models for computer vision has been their inability to retain multiple sources of information in a modular fashion. For instance, given a network that has been trained on a source task, we would like to re-
Externí odkaz:
http://arxiv.org/abs/2308.13957
Language models can be prompted to reason through problems in a manner that significantly improves performance. However, \textit{why} such prompting improves performance is unclear. Recent work showed that using logically \textit{invalid} Chain-of-Th
Externí odkaz:
http://arxiv.org/abs/2307.10573
Autor:
Cong, Yezhen, Khanna, Samar, Meng, Chenlin, Liu, Patrick, Rozi, Erik, He, Yutong, Burke, Marshall, Lobell, David B., Ermon, Stefano
Unsupervised pre-training methods for large vision models have shown to enhance performance on downstream supervised tasks. Developing similar techniques for satellite imagery presents significant opportunities as unlabelled data is plentiful and the
Externí odkaz:
http://arxiv.org/abs/2207.08051