Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Majumder, Soumajit"'
Publikováno v:
Transactions on Machine Learning Research - 2024
Previous studies have demonstrated that not each sample in a dataset is of equal importance during training. Data pruning aims to remove less important or informative samples while still achieving comparable results as training on the original (untru
Externí odkaz:
http://arxiv.org/abs/2412.10091
Fine-tuning large pre-trained foundation models, such as the 175B GPT-3, has attracted more attention for downstream tasks recently. While parameter-efficient fine-tuning methods have been proposed and proven effective without retraining all model pa
Externí odkaz:
http://arxiv.org/abs/2407.01320
Implicit models such as Deep Equilibrium Models (DEQs) have garnered significant attention in the community for their ability to train infinite layer models with elegant solution-finding procedures and constant memory footprint. However, despite seve
Externí odkaz:
http://arxiv.org/abs/2307.08013
Segmenting objects of interest in an image is an essential building block of applications such as photo-editing and image analysis. Under interactive settings, one should achieve good segmentations while minimizing user input. Current deep learning-b
Externí odkaz:
http://arxiv.org/abs/2010.09672
Autor:
Majumder, Soumajit, Yao, Angela
In current interactive instance segmentation works, the user is granted a free hand when providing clicks to segment an object; clicks are allowed on background pixels and other object instances far from the target object. This form of interaction is
Externí odkaz:
http://arxiv.org/abs/2010.09140
Autor:
Majumder, Soumajit, Yao, Angela
In interactive instance segmentation, users give feedback to iteratively refine segmentation masks. The user-provided clicks are transformed into guidance maps which provide the network with necessary cues on the whereabouts of the object of interest
Externí odkaz:
http://arxiv.org/abs/1812.02967
Emerging technologies with asymptotic zero power dissipation, such as quantum computing, require the logical operations to be done in a reversible manner. In recent years, the problem of synthesizing Boolean functions in the reversible logic domain h
Externí odkaz:
http://arxiv.org/abs/1405.6073
Publikováno v:
Pattern Recognition
Segmenting objects of interest in an image is an essential building block of applications such as photo-editing and image analysis. Under interactive settings, one should achieve good segmentations while minimizing user input. Current deep learning-b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1492d50a249e2ea38c97a439a1a9bf93
http://europepmc.org/articles/PMC7972736
http://europepmc.org/articles/PMC7972736
Publikováno v:
Reversible Computation: 6th International Conference, RC 2014, Kyoto, Japan, July 10-11, 2014. Proceedings; 2014, p95-110, 16p
Publikováno v:
2014 IEEE Fourth International Conference on Consumer Electronics Berlin (ICCE-Berlin; 2014, p484-488, 5p