A Caltech Library Service

Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection

Chang, Nadine and Yu, Zhiding and Wang, Yu-Xiong and Anandkumar, Animashree and Fidler, Sanja and Alvarez, Jose M. (2021) Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection. . (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


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.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Record Number:CaltechAUTHORS:20210510-134322482
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:109038
Deposited By: Tony Diaz
Deposited On:10 May 2021 20:56
Last Modified:10 May 2021 20:56

Repository Staff Only: item control page