paper-with-me

홈 › Papers

Learning to Detect and Retrieve Objects from Unlabeled Videos

2019-05-27 · Elad Amrani, Rami Ben-Ari, Tal Hakim, Alex Bronstein

Learning an object detector or retrieval requires a large data set with manual annotations. Such data sets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose to exploit the natural correlation in narrations and the visual presence of objects in video, to learn an object detector and retrieval without any manual labeling involved. We pose the problem as weakly supervised learning with noisy labels, and propose a novel object detection paradigm under these constraints. We handle the background rejection by using contrastive samples and confront the high level of label noise with a new clustering score. Our evaluation is based on a set of 11 manually annotated objects in over 5000 frames. We show comparison to a weakly-supervised approach as baseline and provide a strongly labeled upper bound.

📄 PDF Abstract BibTeX arXiv:1905.11137

Code (1)

Yan107351111/SSOD pytorch

Tasks

ClusteringLearning with noisy labelsNovel Object DetectionObjectobject-detectionObject DetectionRetrievalWeakly-supervised Learning

Similar Papers 제목 키워드 기반

MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos

2024-05-23 · Yihong Sun, Bharath Hariharan

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 looke…

Motion SegmentationObjectobject-detectionObject Detection+5

Two Video Data Sets for Tracking and Retrieval of Out of Distribution Objects

2022-10-05 · Kira Maag, Robin Chan, Svenja Uhlemeyer, Kamil Kowol 외

In this work we present two video test data sets for the novel computer vision (CV) task of out of distribution tracking (OOD tracking). Here, OOD objects are understood as objects with a semantic class outside the seman…

Image SegmentationRetrievalSemantic Segmentation

A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs

2020-11-10 · Juntao Tan, Changkyu Song, Abdeslam Boularias

This paper presents a new self-supervised system for learning to detect novel and previously unseen categories of objects in images. The proposed system receives as input several unlabeled videos of scenes containing var…

Clusteringobject-detectionObject DetectionSelf-Supervised Learning+1

Object-Level Targeted Selection via Deep Template Matching

2022-07-05 · Suraj Kothawade, Donna Roy, Michele Fenzi, Elmar Haussmann 외

Retrieving images with objects that are semantically similar to objects of interest (OOI) in a query image has many practical use cases. A few examples include fixing failures like false negatives/positives of a learned …

Autonomous DrivingImage RetrievalObjectRetrieval+1

LogSTOP: Temporal Scores over Prediction Sequences for Matching and Retrieval

2025-10-07 · Avishree Khare, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos 외 arxiv

Neural models such as YOLO and HuBERT can be used to detect local properties such as objects ("car") and emotions ("angry") in individual frames of videos and audio clips respectively. The likelihood of these detections …

Video Retrieval