|
Aaron Sun I'm a PhD Student at UMass Amherst studying Computer Vision under Subhransu Maji, currently focusing on improving identity-preserving generation for scientific accuracy on fine-grained domains. |
|
Research |
|
Not All Birds Look The Same: Identity-Preserving Generation For Birds
Aaron Sun, Oindrila Saha, Subhransu Maji In submission arXiv We introduce the NABirds Look-Alikes (NABLA) dataset, a dataset for identity-preserving generation for birds, and show how training on proxy identity pairs improves performance on seen and unseen species. |
|
The Merlin L48 Spectrogram Dataset
Aaron Sun, Subhransu Maji, Grant Van Horn NeurIPS 2025 NeurIPS25 / arXiv / code We introduce the L48 Spectrogram dataset, a fine-grained, real-world benchmark for SPML learning, and propose a new regularization method which improves existing techniques. |
|
Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships
Rangel Daroya, Aaron Sun, Subhransu Maji CVPR 2024 CVPR24 / arXiv / code We present a method of task representation using box embeddings and demonstrate how they are able to capture asymmetric relationships between tasks and generalize to unseen tasks. |
|
ZeoNet: 3D convolutional neural networks for predicting adsorption in nanoporous zeolites
Yachan Liu, Gustavo Perez, Zezhou Cheng, Aaron Sun, Sam Hoover, Wei Fan, Subhransu Maji, Peng Bai Journal of Materials Chemistry 2023 paper / code We present a representation learning framework using CNNs and 3D volumetric representations for predicting adsorption in zeolites. |
|
COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification
Rangel Daroya, Aaron Sun, Subhransu Maji ICCVW 2023 ICCVW23 / arXiv / code We present a set of metrics that utilize vision priors to effectively assess the performance of saliency methods on image classification tasks. |