Related papers: Static-Dynamic Co-Teaching for Class-Incremental 3…

Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a…

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of…

Incremental object detection (IOD) aims to cultivate an object detector that can continuously localize and recognize novel classes while preserving its performance on previous classes. Existing methods achieve certain success by improving…

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…

Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few…

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…

Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on…

3D object classification has attracted appealing attentions in academic researches and industrial applications. However, most existing methods need to access the training data of past 3D object classes when facing the common real-world…

Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of…

Service robots, in general, have to work independently and adapt to the dynamic changes happening in the environment in real-time. One important aspect in such scenarios is to continually learn to recognize newer object categories when they…

We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale training, and their variants are aiming at preparing…

We investigate the problem of incremental learning for object counting, where a method must learn to count a variety of object classes from a sequence of datasets. A na\"ive approach to incremental object counting would suffer from…

To address the problem of catastrophic forgetting due to the invisibility of old categories in sequential input, existing work based on relatively simple categorization tasks has made some progress. In contrast, video captioning is a more…

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…

Developing deep learning models that effectively learn object-centric representations, akin to human cognition, remains a challenging task. Existing approaches facilitate object discovery by representing objects as fixed-size vectors,…

In this paper, we present a new dynamic collaborative network for semi-supervised 3D vessel segmentation, termed DiCo. Conventional mean teacher (MT) methods typically employ a static approach, where the roles of the teacher and student…

Real-time object detectors like YOLO achieve exceptional performance when trained on large datasets for multiple epochs. However, in real-world scenarios where data arrives incrementally, neural networks suffer from catastrophic forgetting,…

When we fine-tune a well-trained deep learning model for a new set of classes, the network learns new concepts but gradually forgets the knowledge of old training. In some real-life applications, we may be interested in learning new classes…

Recently, many researchers have attempted to improve deep learning-based object detection models, both in terms of accuracy and operational speeds. However, frequently, there is a trade-off between speed and accuracy of such models, which…