MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos
Embodied agents must detect and localize objects of interest, e.g. traffic participants for self-driving cars. Supervision in the form of bounding boxes for this task is extremely expensive. As such, prior work has looked at unsupervised instance detection and segmentation, but in the absence of annotated boxes, it is unclear how pixels must be grouped into objects and which objects are of interest. This results in over-/under-segmentation and irrelevant objects. Inspired by human visual system and practical applications, we posit that the key missing cue for unsupervised detection is motion: objects of interest are typically mobile objects that frequently move and their motions can specify separate instances. In this paper, we propose MOD-UV, a Mobile Object Detector learned from Unlabeled Videos only. We begin with instance pseudo-labels derived from motion segmentation, but introduce a novel training paradigm to progressively discover small objects and static-but-mobile objects that are missed by motion segmentation. As a result, though only learned from unlabeled videos, MOD-UV can detect and segment mobile objects from a single static image. Empirically, we achieve state-of-the-art performance in unsupervised mobile object detection on Waymo Open, nuScenes, and KITTI Datasets without using any external data or supervised models. Code is available at https://github.com/YihongSun/MOD-UV.
Code (1)
Tasks
Motion SegmentationObjectobject-detectionObject DetectionSegmentationSelf-Driving CarsSemantic SegmentationUnsupervised Object DetectionUnsupervised Object SegmentationSimilar Papers 제목 키워드 기반
An Approach for Self-Training Audio Event Detectors Using Web Data
Audio Event Detection (AED) aims to recognize sounds within audio and video recordings. AED employs machine learning algorithms commonly trained and tested on annotated datasets. However, available datasets are limited i…
DiversityEvent DetectionSelf-Learning Camera: Autonomous Adaptation of Object Detectors to Unlabeled Video Streams
Learning object detectors requires massive amounts of labeled training samples from the specific data source of interest. This is impractical when dealing with many different sources (e.g., in camera networks), or consta…
Multi-Task LearningObjectSelf-LearningSemi-supervised 3D Object Detection via Temporal Graph Neural Networks
3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and time-consuming…
3D Object DetectionAutonomous DrivingGraph Neural Networkobject-detection+1Self-Supervised Learning of Object Segmentation from Unlabeled RGB-D Videos
This work proposes a self-supervised learning system for segmenting rigid objects in RGB images. The proposed pipeline is trained on unlabeled RGB-D videos of static objects, which can be captured with a camera carried b…
Contrastive LearningGraph MatchingObjectPoint Cloud Registration+2Human-AI Ensembles Improve Deepfake Detection in Low-to-Medium Quality Videos
Deepfake detection is widely framed as a machine learning problem, yet how humans and AI detectors compare under realistic conditions remains poorly understood. We evaluate 200 human participants and 95 state-of-the-art …
DeepFake Detection