Related papers: Augmented Box Replay: Overcoming Foreground Shift …
Existing Incremental Object Detection (IOD) methods partially alleviate catastrophic forgetting when incrementally detecting new objects in real-world scenarios. However, many of these methods rely on the assumption that unlabeled old-class…
Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future tasks. Most existing approaches rely on model-free methods with…
Object detection limits its recognizable categories during the training phase, in which it can not cover all objects of interest for users. To satisfy the practical necessity, the incremental learning ability of the detector becomes a…
Class incremental learning aims to solve a problem that arises when continuously adding unseen class instances to an existing model This approach has been extensively studied in the context of image classification; however its applicability…
In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…
Incremental Object Detection (IOD) aims to continuously learn new object classes without forgetting previously learned ones. A persistent challenge is catastrophic forgetting, primarily attributed to background shift in conventional…
In this work, we focus on continual semantic segmentation (CSS), where segmentation networks are required to continuously learn new classes without erasing knowledge of previously learned ones. Although storing images of old classes and…
This paper focuses on a novel and challenging detection scenario: A majority of true objects/instances is unlabeled in the datasets, so these missing-labeled areas will be regarded as the background during training. Previous art on this…
Traditional object detection are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will leads to catastrophic forgetting. Knowledge distillation is a straightforward…
Incremental learning aims to enable machine learning models to continuously acquire new knowledge given new classes, while maintaining the knowledge already learned for old classes. Saving a subset of training samples of previously seen…
Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already…
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 first identify three…
Incremental or continual learning has been extensively studied for image classification tasks to alleviate catastrophic forgetting, a phenomenon that earlier learned knowledge is forgotten when learning new concepts. For class incremental…
Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, i.e., adapting the original model trained on a set of classes to additionally detect objects of new classes, in the absence…
Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic…
Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data. Most existing object…
In contrast to the incremental classification task, the incremental detection task is characterized by the presence of data ambiguity, as an image may have differently labeled bounding boxes across multiple continuous learning stages. This…
Despite their effectiveness in a wide range of tasks, deep architectures suffer from some important limitations. In particular, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are required to update their…
Humans can incrementally learn to do new visual detection tasks, which is a huge challenge for today's computer vision systems. Incrementally trained deep learning models lack backwards transfer to previously seen classes and suffer from a…
In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On…