Learning from limited and imperfect data (Record no. 433258)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02862nam a2200253 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 250304b |||||||| |||| 00| 0 eng d |
| 041 ## - LANGUAGE CODE | |
| Language code of text/sound track or separate title | en |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 006.3 |
| Item number | RAN |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Rangwani, Harsh |
| 245 ## - TITLE STATEMENT | |
| Title | Learning from limited and imperfect data |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) | |
| Place of publication, distribution, etc | Bangalore : |
| Name of publisher, distributor, etc | Indian Institute of Science, |
| Date of publication, distribution, etc | 2024. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | xi, 302 p. : |
| Other physical details | col. ill. |
| Accompanying material | e-Thesis |
| Size of unit | 58.31 Mb |
| 500 ## - GENERAL NOTE | |
| General note | Includes bibliographical references |
| 502 ## - DISSERTATION NOTE | |
| Dissertation note | PhD;2024;Computational and Data Sciences<br/> |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc | Deep Neural Networks have demonstrated orders of magnitude improvement in capabilities over the years after AlexNet won the ImageNet challenge in 2012. One of the major reasons for this success is the availability of large-scale, well-curated datasets. These datasets (e.g. ImageNet, MSCOCO, etc.) are often manually balanced across categories (classes) to facilitate learning of all the categories. This curation process is often expensive and requires throwing away precious annotated data to balance the frequency across classes. This is because the distribution of data in the world (e.g., internet, etc.) significantly differs from the well-curated datasets and is often over-populated with samples from common categories. The algorithms designed for well-curated datasets perform suboptimally when used for learning from imperfect datasets with long-tailed imbalances and distribution shifts.To expand the use of deep models, it is essential to overcome the labor-intensive curation process by developing robust algorithms that can learn from diverse, real-world data distributions. Toward this goal, we develop practical algorithms for Deep Neural Networks which can learn from limited and imperfect data present in the real world. This thesis is divided into four segments, each covering a scenario of learning from limited or imperfect data. The first part of the thesis focuses on Learning Generative Models from Long-Tail Data, where we mitigate the mode-collapse and enable diverse aesthetic image generations for tail (minority) classes. In the second part, we enable effective generalization on tail classes through Inductive Regularization schemes, which allow tail classes to generalize as effectively as the head classes without requiring explicit generation of images. In the third part, we develop algorithms for Optimizing Relevant Metrics for learning from long-tailed data with limited annotation (semi-supervised), followed by the fourth part, which focuses on the Efficient Domain Adaptation of the model to various domains with zero to very few labeled samples. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name as entry element | Deep Neural Networks |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name as entry element | Data Curation |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name as entry element | Long-Tailed Data |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name as entry element | Imperfect data |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name as entry element | Curation |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Advised by Venkatesh Babu, R |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | https://etd.iisc.ac.in/handle/2005/6815 |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | Thesis |
No items available.
