Search Results for author: Maitreya Patel

Found 10 papers, 5 papers with code

$λ$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space

no code implementations7 Feb 2024 Maitreya Patel, Sangmin Jung, Chitta Baral, Yezhou Yang

The primary bottlenecks include 1) Intensive training resource requirements, 2) Hyper-parameter sensitivity leading to inconsistent outputs, and 3) Balancing the intricacies of novel visual concept and composition alignment.

Concept Alignment Philosophy

ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations

no code implementations7 Dec 2023 Maitreya Patel, Changhoon Kim, Sheng Cheng, Chitta Baral, Yezhou Yang

The T2I prior model alone adds a billion parameters compared to the Latent Diffusion Models, which increases the computational and high-quality data requirements.

Contrastive Learning

WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models

no code implementations7 Jun 2023 Changhoon Kim, Kyle Min, Maitreya Patel, Sheng Cheng, Yezhou Yang

The rapid advancement of generative models, facilitating the creation of hyper-realistic images from textual descriptions, has concurrently escalated critical societal concerns such as misinformation.

Misinformation

ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models

1 code implementation7 Jun 2023 Maitreya Patel, Tejas Gokhale, Chitta Baral, Yezhou Yang

To quantify the ability of T2I models in learning and synthesizing novel visual concepts (a. k. a.

Concept Alignment

Reasoning about Actions over Visual and Linguistic Modalities: A Survey

no code implementations15 Jul 2022 Shailaja Keyur Sampat, Maitreya Patel, Subhasish Das, Yezhou Yang, Chitta Baral

'Actions' play a vital role in how humans interact with the world and enable them to achieve desired goals.

Common Sense Reasoning

CinC-GAN for Effective F0 prediction for Whisper-to-Normal Speech Conversion

1 code implementation18 Aug 2020 Maitreya Patel, Mirali Purohit, Jui Shah, Hemant A. Patil

The CycleGAN-based method uses two different models, one for Mel Cepstral Coefficients (MCC) mapping, and another for F0 prediction, where F0 is highly dependent on the pre-trained model of MCC mapping.

Voice Conversion

AdaGAN: Adaptive GAN for Many-to-Many Non-Parallel Voice Conversion

1 code implementation25 Sep 2019 Maitreya Patel, Mirali Purohit, Mihir Parmar, Nirmesh J. Shah, Hemant A. Patil

In this paper, we propose a novel style transfer architecture, which can also be extended to generate voices even for target speakers whose data were not used in the training (i. e., case of zero-shot learning).

Generative Adversarial Network Style Transfer +2

Precipitation Nowcasting: Leveraging bidirectional LSTM and 1D CNN

no code implementations24 Oct 2018 Maitreya Patel, Anery Patel, Dr. Ranendu Ghosh

Short-term rainfall forecasting, also known as precipitation nowcasting has become a potentially fundamental technology impacting significant real-world applications ranging from flight safety, rainstorm alerts to farm irrigation timings.

Time Series Time Series Forecasting +1

Cannot find the paper you are looking for? You can Submit a new open access paper.