Meta Guided Metric Learner for Overcoming Class Confusion in Few-Shot Road Object Detection
This work addresses the challenge of detecting rare road objects in autonomous driving, offering a novel method to reduce class confusion, though it is incremental as it builds on existing meta and metric learning techniques.
The paper tackles class confusion and base class forgetting in few-shot object detection for road objects by introducing a Meta Guided Metric Learner (MGML), which improves state-of-the-art performance by up to 11 mAP points on the India Driving Dataset and 5.8 mAP on PASCAL VOC splits with only 10 examples per novel class.
Localization and recognition of less-occurring road objects have been a challenge in autonomous driving applications due to the scarcity of data samples. Few-Shot Object Detection techniques extend the knowledge from existing base object classes to learn novel road objects given few training examples. Popular techniques in FSOD adopt either meta or metric learning techniques which are prone to class confusion and base class forgetting. In this work, we introduce a novel Meta Guided Metric Learner (MGML) to overcome class confusion in FSOD. We re-weight the features of the novel classes higher than the base classes through a novel Squeeze and Excite module and encourage the learning of truly discriminative class-specific features by applying an Orthogonality Constraint to the meta learner. Our method outperforms State-of-the-Art (SoTA) approaches in FSOD on the India Driving Dataset (IDD) by upto 11 mAP points while suffering from the least class confusion of 20% given only 10 examples of each novel road object. We further show similar improvements on the few-shot splits of PASCAL VOC dataset where we outperform SoTA approaches by upto 5.8 mAP accross all splits.