ODAM : Gradient-based Instance-Specific Visual Explanations for Object Detection

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

3 Scopus Citations
View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationThe Eleventh International Conference on Learning Representations
PublisherInternational Conference on Learning Representations, ICLR
Publication statusPublished - May 2023

Publication series

NameInternational Conference on Learning Representations, ICLR

Conference

Title11th International Conference on Learning Representations (ICLR 2023)
LocationHybrid
PlaceRwanda
CityKigali
Period1 - 5 May 2023

Abstract

We propose the gradient-weighted Object Detector Activation Maps (ODAM), a visualized explanation technique for interpreting the predictions of object detectors. Utilizing the gradients of detector targets flowing into the intermediate feature maps, ODAM produces heat maps that show the influence of regions on the detector's decision for each predicted attribute. Compared to previous works classification activation maps (CAM), ODAM generates instance-specific explanations rather than class-specific ones. We show that ODAM is applicable to both one-stage detectors and two-stage detectors with different types of detector backbones and heads, and produces higher-quality visual explanations than the state-of-the-art both effectively and efficiently. We next propose a training scheme, Odam-Train, to improve the explanation ability on object discrimination of the detector through encouraging consistency between explanations for detections on the same object, and distinct explanations for detections on different objects. Based on the heat maps produced by ODAM with Odam-Train, we propose Odam-NMS, which considers the information of the model's explanation for each prediction to distinguish the duplicate detected objects. We present a detailed analysis of the visualized explanations of detectors and carry out extensive experiments to validate the effectiveness of the proposed ODAM. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

Citation Format(s)

ODAM: Gradient-based Instance-Specific Visual Explanations for Object Detection. / Zhao, Chenyang; Chan, Antoni B.
The Eleventh International Conference on Learning Representations. International Conference on Learning Representations, ICLR, 2023. (International Conference on Learning Representations, ICLR ).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review