Related papers: Learning Non-target Knowledge for Few-shot Semanti…

Few-shot named entity recognition (NER) has shown remarkable progress in identifying entities in low-resource domains. However, few-shot NER methods still struggle with out-of-domain (OOD) examples due to their reliance on manual labeling…

Zero-shot incremental learning aims to enable the model to generalize to new classes without forgetting previously learned classes. However, the semantic gap between old and new sample classes can lead to catastrophic forgetting.…

Few-shot learning aims to learn novel categories from very few samples given some base categories with sufficient training samples. The main challenge of this task is the novel categories are prone to dominated by color, texture, shape of…

We present a novel framework for self-supervised grasped object segmentation with a robotic manipulator. Our method successively learns an agnostic foreground segmentation followed by a distinction between manipulator and object solely by…

Few-shot learning models learn representations with limited human annotations, and such a learning paradigm demonstrates practicability in various tasks, e.g., image classification, object detection, etc. However, few-shot object detection…

Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection…

Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples. Prototype learning, where the support feature yields a singleor several prototypes by averaging global and local object information,…

Generalized few-shot semantic segmentation (GFSS) aims to segment objects of both base and novel classes, using sufficient samples of base classes and few samples of novel classes. Representative GFSS approaches typically employ a two-phase…

For many natural language processing (NLP) tasks the amount of annotated data is limited. This urges a need to apply semi-supervised learning techniques, such as transfer learning or meta-learning. In this work we tackle Named Entity…

Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation. Recently, a popular solution is leveraging RGB-D features of large-scale synthetic data and directly applying the…

Grounding DINO and the Segment Anything Model (SAM) have achieved impressive performance in zero-shot object detection and image segmentation, respectively. Together, they have a great potential to revolutionize applications in zero-shot…

Accelerator-based neutrino experiments with high-intensity proton beams and advanced detector technologies provide a powerful and complementary approach to probing physics beyond the Standard Model. The MiniBooNE experiment at Fermilab…

In visual recognition tasks, few-shot learning requires the ability to learn object categories with few support examples. Its re-popularity in light of the deep learning development is mainly in image classification. This work focuses on…

Infrared small target detection is a key technique in infrared search and tracking (IRST) systems. Although deep learning has been widely used in the vision tasks of visible light images recently, it is rarely used in infrared small target…

When confronted with objects of unknown types in an image, humans can effortlessly and precisely tell their visual boundaries. This recognition mechanism and underlying generalization capability seem to contrast to state-of-the-art image…

To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm. However, most existing methods only focus on the…

Knowledge graphs (KGs), containing many entity-relation-entity triples, provide rich information for downstream applications. Although extracting triples from unstructured texts has been widely explored, most of them require a large number…

Recent methods focus on learning a unified semantic-aligned visual representation to transfer knowledge between two domains, while ignoring the effect of semantic-free visual representation in alleviating the biased recognition problem. In…

Few-shot semantic segmentation (FSS) aims to segment objects of novel categories in the query images given only a few annotated support samples. Existing methods primarily build the image-level correlation between the support target object…

State-of-the-art vision-language models (VLMs) suffer from a critical failure in understanding negation, often referred to as affirmative bias. This limitation is particularly severe in described object detection (DOD) tasks. To address…