Improving Distant 3D Object Detection Using 2D Box Supervision
Improving the detection of distant 3d objects is an important yet challenging task. For camera-based 3D perception, the annotation of 3d bounding relies heavily on LiDAR for accurate depth information. As such, the distance of annotation is often limited due to the sparsity of LiDAR points on distant objects, which hampers the capability of existing detectors for long-range scenarios. We address this challenge by considering only 2D box supervision for distant objects since they are easy to annotate. We propose LR3D, a framework that learns to recover the missing depth of distant objects. LR3D adopts an implicit projection head to learn the generation of mapping between 2D boxes and depth using the 3D supervision on close objects. This mapping allows the depth estimation of distant objects conditioned on their 2D boxes, making long-range 3D detection with 2D supervision feasible. Experiments show that without distant 3D annotations, LR3D allows camera-based methods to detect distant objects (over 200m) with comparable accuracy to full 3D supervision. Our framework is general, and could widely benefit 3D detection methods to a large extent.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Object DetectionDepth EstimationObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Open-Domain Event Detection using Distant Supervision
This paper introduces open-domain event detection, a new event detection paradigm to address issues of prior work on restricted domains and event annotation. The goal is to detect all kinds of events regardless of domain…
Event DetectionOpen-Domain Question AnsweringQuestion AnsweringPseudo-labelling Enhanced Media Bias Detection
Leveraging unlabelled data through weak or distant supervision is a compelling approach to developing more effective text classification models. This paper proposes a simple but effective data augmentation method, which …
Bias DetectionData Augmentationtext-classificationText ClassificationLow-resource Cross-lingual Event Type Detection via Distant Supervision with Minimal Effort
Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm
NLP tasks are often limited by scarcity of manually annotated data. In social media sentiment analysis and related tasks, researchers have therefore used binarized emoticons and specific hashtags as forms of distant supe…
DiversitySarcasm DetectionSentiment AnalysisTransfer LearningKnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision
Modern models of event causality detection (ECD) are mainly based on supervised learning from small hand-labeled corpora. However, hand-labeled training data is expensive to produce, low coverage of causal expressions an…
Data Augmentation