Milind Napthade

Milind Napthade

Auto-generated profile, based on publicly available information

Milind Napthade

Capital One, San Francisco, CA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YYYue Yao
Yue Yao
LZLiang Zheng
Liang Zheng
XYXiaodong Yang
Xiaodong Yang
MNMilind Napthade
Milind Napthade
Tom GedeonTom Gedeon
Tom Gedeon
This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data. Between synthetic and real, a two-level domain gap exists, involving content level and appearance level. While the latter is concerned with appearance style, the former problem arises from a different mechanism, i.e., content mismatch in attributes such as camera viewpoint, object placement and lighting conditions. In contrast to the widely-studied appearance-level gap, the content-level discrepancy has not been broadly studied. To address the content-level misalignment, we propose an attribute descent approach that automatically optimizes engine attributes to enable synthetic data to approximate real-world data. We verify our method on object-centric tasks, wherein an object takes up a major portion of an image. In these tasks, the search space is relatively small, and the optimization of each attribute yields sufficiently obvious supervision signals. We collect a new synthetic asset VehicleX, and reformat and reuse existing the synthetic assets ObjectX and PersonX. Extensive experiments on image classification and object re-identification confirm that adapted synthetic data can be effectively used in three scenarios: training with synthetic data only, training data augmentation and numerically understanding dataset content.