Related papers: Better Matching, Less Forgetting: A Quality-Guided…
In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model…
Object detection models shipped with camera-equipped edge devices cannot cover the objects of interest for every user. Therefore, the incremental learning capability is a critical feature for a robust and personalized object detection…
Class-Incremental learning (CIL) refers to the ability of artificial agents to integrate new classes as they appear in a stream. It is particularly interesting in evolving environments where agents have limited access to memory and…
Conditional Flow Matching (CFM), a simulation-free method for training continuous normalizing flows, provides an efficient alternative to diffusion models for key tasks like image and video generation. The performance of CFM in solving…
Catastrophic forgetting is a critical chanllenge for incremental object detection (IOD). Most existing methods treat the detector monolithically, relying on instance replay or knowledge distillation without analyzing component-specific…
High-dimensional integration with respect to complex target measures remains a fundamental challenge in computational science. While Flow Matching (FM) offers a powerful paradigm for constructing continuous-time transport maps, its…
Task-driven features learned by modern object detectors optimize end task loss yet often capture shortcut correlations that fail to reflect underlying annotation structure. Such representations limit transfer, interpretability, and…
Catastrophic forgetting is a problem of neural networks that loses the information of the first task after training the second task. Here, we propose a method, i.e. incremental moment matching (IMM), to resolve this problem. IMM…
Deformable image registration is inherently a multi-objective optimization (MOO) problem, requiring a delicate balance between image similarity and deformation regularity. These conflicting objectives often lead to poor optimization…
Recent multimodal large language models (MLLMs) have demonstrated strong capabilities in image quality assessment (IQA) tasks. However, adapting such large-scale models is computationally expensive and still relies on substantial Mean…
Collecting high quality data for object detection tasks is challenging due to the inherent subjectivity in labeling the boundaries of an object. This makes it difficult to not only collect consistent annotations across a dataset but also to…
Recent advances in deep learning algorithms have shown impressive progress in image copy-move forgery detection (CMFD). However, these algorithms lack generalizability in practical scenarios where the copied regions are not present in the…
Video camouflaged object detection (VCOD) is challenging due to dynamic environments. Existing methods face two main issues: (1) SAM-based methods struggle to separate camouflaged object edges due to model freezing, and (2) MLLM-based…
In real-world applications, an object detector often encounters object instances from new classes and needs to accommodate them effectively. Previous work formulated this critical problem as incremental object detection (IOD), which assumes…
In autonomous driving, vision-centric 3D object detection recognizes and localizes 3D objects from RGB images. However, due to high annotation costs and diverse outdoor scenes, training data often fails to cover all possible test scenarios,…
Camouflaged object detection (COD) primarily relies on semantic or instance segmentation methods. While these methods have made significant advancements in identifying the contours of camouflaged objects, they may be inefficient or…
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…
As machine learning systems increasingly rely on data subject to privacy regulation, selectively unlearning specific information from trained models has become essential. In image classification, this involves removing the influence of…
Large-scale pre-trained models (PTMs) provide remarkable zero-shot classification capability covering a wide variety of object classes. However, practical applications do not always require the classification of all kinds of objects, and…
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…