Expanding Object Detector's Horizon: Incremental Learning Framework for Object Detection in Videos
Over the last several years it has been shown that image-based object detectors are sensitive to the training data and often fail to generalize to examples that fall outside the original training sample domain (e.g., videos). A number of domain adaptation (DA) techniques have been proposed to address this problem. DA approaches are designed to adapt a fixed complexity model to the new (e.g., video) domain. We posit that unlabeled data should not only allow adaptation, but also improve (or at least maintain) performance on the original and other domains by dynamically adjusting model complexity and parameters. We call this notion domain expansion. To this end, we develop a new scalable and accurate incremental object detection algorithm, based on several extensions of large-margin embedding (LME). Our detection model consists of an embedding space and multiple class prototypes in that embedding space, that represent object classes; distance to those prototypes allows us to reason about multi-class detection. By incrementally detecting object instances in video and adding confident detections into the model, we are able to dynamically adjust the complexity of the detector over time by instantiating new prototypes to span all domains the model has seen. We test performance of our approach by expanding an object detector trained on ImageNet to detect objects in ego-centric videos of Activity Daily Living (ADL) dataset and challenging YouTube Objects (YTO) dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationIncremental LearningObjectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN
The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep learning networks are ill-equipped for …
Incremental LearningKnowledge DistillationObjectRegion ProposalFew-Shot Batch Incremental Road Object Detection via Detector Fusion
Incremental few-shot learning has emerged as a new and challenging area in deep learning, whose objective is to train deep learning models using very few samples of new class data, and none of the old class data. In this…
Few-Shot Learningobject-detectionObject DetectionYOLO-IOD: Towards Real Time Incremental Object Detection
Current methods for incremental object detection (IOD) primarily rely on Faster R-CNN or DETR series detectors; however, these approaches do not accommodate the real-time YOLO detection frameworks. In this paper, we firs…
parameter-efficient fine-tuningKnowledge DistillationIncremental LearningObject DetectionEW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer
Real-world object detection must operate in evolving environments where new classes emerge, domains shift, and unseen objects must be identified as "unknown": all without accessing prior data. We introduce Evolving World…
Incremental LearningDomain AdaptationObject DetectionScene Graph Modification as Incremental Structure Expanding
A scene graph is a semantic representation that expresses the objects, attributes, and relationships between objects in a scene. Scene graphs play an important role in many cross modality tasks, as they are able to captu…