Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Horton, Maxwell"'
Autor:
Mehta, Sachin, Horton, Maxwell, Faghri, Fartash, Sekhavat, Mohammad Hossein, Najibi, Mahyar, Farajtabar, Mehrdad, Tuzel, Oncel, Rastegari, Mohammad
Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise similarity computation in contrastive loss between image and text pairs po
Externí odkaz:
http://arxiv.org/abs/2404.15653
Autor:
Mehta, Sachin, Sekhavat, Mohammad Hossein, Cao, Qingqing, Horton, Maxwell, Jin, Yanzi, Sun, Chenfan, Mirzadeh, Iman, Najibi, Mahyar, Belenko, Dmitry, Zatloukal, Peter, Rastegari, Mohammad
The reproducibility and transparency of large language models are crucial for advancing open research, ensuring the trustworthiness of results, and enabling investigations into data and model biases, as well as potential risks. To this end, we releas
Externí odkaz:
http://arxiv.org/abs/2404.14619
Autor:
Salehi, Mohammadreza, Farajtabar, Mehrdad, Horton, Maxwell, Faghri, Fartash, Pouransari, Hadi, Vemulapalli, Raviteja, Tuzel, Oncel, Farhadi, Ali, Rastegari, Mohammad, Mehta, Sachin
Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on image classification tasks, it lacks object localization capabilities. Th
Externí odkaz:
http://arxiv.org/abs/2310.14108
Over the past several years, the synchronization between audio and visual signals has been leveraged to learn richer audio-visual representations. Aided by the large availability of unlabeled videos, many unsupervised training frameworks have demonst
Externí odkaz:
http://arxiv.org/abs/2310.03937
Autor:
Nunez, Elvis, Merth, Thomas, Prabhu, Anish, Farajtabar, Mehrdad, Rastegari, Mohammad, Mehta, Sachin, Horton, Maxwell
Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection. Training with smaller resolutions enables faster training at the expense of a drop in accuracy. Conversely, training
Externí odkaz:
http://arxiv.org/abs/2309.04502
Publikováno v:
Transactions on Machine Learning Research 2835-8856 (2024)
Modern deep learning approaches usually utilize modality-specific processing. For example, the most common deep learning approach to image classification involves decoding image file bytes into an RGB tensor which is passed into a neural network. Ins
Externí odkaz:
http://arxiv.org/abs/2306.00238
Autor:
Mehta, Sachin, Naderiparizi, Saeid, Faghri, Fartash, Horton, Maxwell, Chen, Lailin, Farhadi, Ali, Tuzel, Oncel, Rastegari, Mohammad
State-of-the-art automatic augmentation methods (e.g., AutoAugment and RandAugment) for visual recognition tasks diversify training data using a large set of augmentation operations. The range of magnitudes of many augmentation operations (e.g., brig
Externí odkaz:
http://arxiv.org/abs/2212.10553
Autor:
Lin, Chien-Yu, Prabhu, Anish, Merth, Thomas, Mehta, Sachin, Ranjan, Anurag, Horton, Maxwell, Rastegari, Mohammad
Recent isotropic networks, such as ConvMixer and vision transformers, have found significant success across visual recognition tasks, matching or outperforming non-isotropic convolutional neural networks (CNNs). Isotropic architectures are particular
Externí odkaz:
http://arxiv.org/abs/2207.10237
Autor:
Nunez, Elvis, Horton, Maxwell, Prabhu, Anish, Ranjan, Anurag, Farhadi, Ali, Rastegari, Mohammad
When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource guarantees. Co
Externí odkaz:
http://arxiv.org/abs/2110.04252
Recent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions and (2) wider minima offering improved performance. Previous methods
Externí odkaz:
http://arxiv.org/abs/2102.10472