Related papers: Modeling Missing Annotations for Incremental Learn…

Camouflaged Object Detection (COD) demands models to expeditiously and accurately distinguish objects which conceal themselves seamlessly in the environment. Owing to the subtle differences and ambiguous boundaries, COD is not only a…

Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial…

Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…

Efficient models for remote sensing object counting are urgently required for applications in scenarios with limited computing resources, such as drones or embedded systems. A straightforward yet powerful technique to achieve this is…

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…

Object detectors achieve strong performance under nominal imaging conditions but can fail silently when exposed to blur, noise, compression, adverse weather, or resolution changes. In safety-critical settings, it is therefore insufficient…

Dataset pruning -- selecting a small yet informative subset of training data -- has emerged as a promising strategy for efficient machine learning, offering significant reductions in computational cost and storage compared to alternatives…

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language supervision is an…

Recently, detection of label errors and improvement of label quality in datasets for supervised learning tasks has become an increasingly important goal in both research and industry. The consequences of incorrectly annotated data include…

Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object…

Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty of alleviating catastrophic forgetting since all techniques…

Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, UAV-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors.…

Incremental object detection (IOD) aims to continuously expand the capability of a model to detect novel categories while preserving its performance on previously learned ones. When adopting a transformer-based detection model to perform…

Training deep object detectors requires significant amount of human-annotated images with accurate object labels and bounding box coordinates, which are extremely expensive to acquire. Noisy annotations are much more easily accessible, but…

Object recognition for the most part has been approached as a one-hot problem that treats classes to be discrete and unrelated. Each image region has to be assigned to one member of a set of objects, including a background class,…

We address the problem of weakly supervised object localization where only image-level annotations are available for training object detectors. Numerous methods have been proposed to tackle this problem through mining object proposals.…

Knowledge distillation, a well-known model compression technique, is an active research area in both computer vision and remote sensing communities. In this paper, we evaluate in a remote sensing context various off-the-shelf object…

A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new…

Mask-guided matting networks have achieved significant improvements and have shown great potential in practical applications in recent years. However, simply learning matting representation from synthetic and lack-of-real-world-diversity…

In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural networks are known to suffer under this setting, as they forget previously acquired…