Related papers: State and Scene Enhanced Prototypes for Weakly Sup…
Aerial object detection plays a crucial role in numerous applications. However, most existing methods focus on detecting predefined object categories, limiting their applicability in real-world open scenarios. In this paper, we extend…
Pseudo-Labeling has emerged as a simple yet effective technique for semi-supervised object detection (SSOD). However, the inevitable noise problem in pseudo-labels significantly degrades the performance of SSOD methods. Recent advances…
Recent vision-language pre-trained models (VL-PTMs) have shown remarkable success in open-vocabulary tasks. However, downstream use cases often involve further fine-tuning of VL-PTMs, which may distort their general knowledge and impair…
Weakly-Supervised Semantic Segmentation (WSSS) methods with image-level labels generally train a classification network to generate the Class Activation Maps (CAMs) as the initial coarse segmentation labels. However, current WSSS methods…
Recent advances in Multimodal Large Language Models (MLLMs) have enabled unified multimodal understanding and generation. However, they still struggle with fine-grained text-image alignment, often failing to faithfully depict objects with…
In recent years, object detection has achieved significant progress, especially in the field of open-vocabulary object detection. Unlike traditional methods that rely on predefined categories, open-vocabulary approaches can detect arbitrary…
Existing vision-language model (VLM)-based methods for out-of-distribution (OOD) detection typically rely on similarity scores between input images and in-distribution (ID) text prototypes. However, the modality gap between image and text…
Object Simultaneous Localization and Mapping (SLAM) systems struggle to correctly associate semantically similar objects in close proximity, especially in cluttered indoor environments and when scenes change. We present Semantic Enhancement…
Open-Vocabulary Object Detection (OVOD) has achieved remarkable success in generalizing to novel categories. However, this success often rests on the implicit assumption of domain stationarity. In this work, we provide a principled revisit…
Zero-shot out-of-vocabulary detection (ZS-OOVD) aims to accurately recognize objects of in-vocabulary (IV) categories provided at zero-shot inference, while simultaneously rejecting undefined ones (out-of-vocabulary, OOV) that lack…
Open-vocabulary 3D scene understanding (OV-3D) aims to localize and classify novel objects beyond the closed set of object classes. However, existing approaches and benchmarks primarily focus on the open vocabulary problem within the…
Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, these tokens are less discriminative as they are independent…
One-shot object detection (OSOD) aims to detect all object instances towards the given category specified by a query image. Most existing studies in OSOD endeavor to explore effective cross-image correlation and alleviate the semantic…
Open-world object detection (OWOD) extends traditional object detection to identifying both known and unknown object, necessitating continuous model adaptation as new annotations emerge. Current approaches face significant limitations: 1)…
Semi-supervised object detection (SSOD) based on pseudo-labeling significantly reduces dependence on large labeled datasets by effectively leveraging both labeled and unlabeled data. However, real-world applications of SSOD often face…
Due to the dynamic nature of human language, automatic speech recognition (ASR) systems need to continuously acquire new vocabulary. Out-Of-Vocabulary (OOV) words, such as trending words and new named entities, pose problems to modern ASR…
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…
Weakly-Supervised Change Detection (WSCD) aims to distinguish specific object changes (e.g., objects appearing or disappearing) from background variations (e.g., environmental changes due to light, weather, or seasonal shifts) in paired…
Image segmentation beyond predefined categories is a key challenge in remote sensing, where novel and unseen classes often emerge during inference. Open-vocabulary image Segmentation addresses these generalization issues in traditional…
Weakly supervised visual grounding (VG) aims to locate objects in images based on text descriptions. Despite significant progress, existing methods lack strong cross-modal reasoning to distinguish subtle semantic differences in text…