Nadine Chang

Nadine Chang

Auto-generated profile, based on publicly available information

Nadine Chang

Carnegie Mellon University Carnegie Mellon University Carnegie Mellon University Carnegie Mellon University

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
18 October 2021 in arXiv
Verified
Preprint
Open access
PDF file
NCNadine Chang
Nadine Chang
ZYZhiding Yu
Zhiding Yu
YWYu-Xiong Wang
Yu-Xiong Wang
AAAnima Anandkumar
Anima Anandkumar
SFSanja Fidler
Sanja Fidler
JAJose M. Alvarez
Jose M. Alvarez
Training on datasets with long-tailed distributions has been challenging for major recognition tasks such as classification and detection. To deal with this challenge, image resampling is typically introduced as a simple but effective approach. However, we observe that long-tailed detection differs from classification since multiple classes may be present in one image. As a result, image resampling alone is not enough to yield a sufficiently balanced distribution at the object level. We address object-level resampling by introducing an object-centric memory replay strategy based on dynamic, episodic memory banks. Our proposed strategy has two benefits: 1) convenient object-level resampling without significant extra computation, and 2) implicit feature-level augmentation from model updates. We show that image-level and object-level resamplings are both important, and thus unify them with a joint resampling strategy (RIO). Our method outperforms state-of-the-art long-tailed detection and segmentation methods on LVIS v0.5 across various backbones. Code is available at https://github.com/NVlabs/RIO.

24 June 2023 in arXiv
Verified
Preprint
Open access
PDF file
NCNadine Chang
Nadine Chang
FFFrancesco Ferroni
Francesco Ferroni
MTMichael J. Tarr
Michael J. Tarr
MHMartial Hebert
Martial Hebert
DRDeva Ramanan
Deva Ramanan
Large-scale datasets are essential to modern day deep learning. Advocates argue that understanding these methods requires dataset transparency (e.g. "dataset curation, motivation, composition, collection process, etc..."). However, almost no one has suggested the release of the detailed definitions and visual category examples provided to annotators - information critical to understanding the structure of the annotations present in each dataset. These labels are at the heart of public datasets, yet few datasets include the instructions that were used to generate them. We introduce a new task, Labeling Instruction Generation, to address missing publicly available labeling instructions. In Labeling Instruction Generation, we take a reasonably annotated dataset and: 1) generate a set of examples that are visually representative of each category in the dataset; 2) provide a text label that corresponds to each of the examples. We introduce a framework that requires no model training to solve this task and includes a newly created rapid retrieval system that leverages a large, pre-trained vision and language model. This framework acts as a proxy to human annotators that can help to both generate a final labeling instruction set and evaluate its quality. Our framework generates multiple diverse visual and text representations of dataset categories. The optimized instruction set outperforms our strongest baseline across 5 folds by 7.06 mAP for NuImages and 12.9 mAP for COCO.