Related papers: STAR-IOD: Scale-decoupled Topology Alignment with …

Supervised learning based object detection frameworks demand plenty of laborious manual annotations, which may not be practical in real applications. Semi-supervised object detection (SSOD) can effectively leverage unlabeled data to improve…

We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD). The first stage is a bottom-up proposal generation network that uses raw point cloud as input to generate accurate proposals by…

Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of domain gaps, inability of encoding physical priors, and…

In this paper, we present a self-training method, named ST3D++, with a holistic pseudo label denoising pipeline for unsupervised domain adaptation on 3D object detection. ST3D++ aims at reducing noise in pseudo label generation as well as…

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…

Semi-Supervised Object Detection (SSOD) has been successful in improving the performance of both R-CNN series and anchor-free detectors. However, one-stage anchor-based detectors lack the structure to generate high-quality or flexible…

To accommodate rapid changes in the real world, the cognition system of humans is capable of continually learning concepts. On the contrary, conventional deep learning models lack this capability of preserving previously learned knowledge.…

Multimodal fusion, leveraging data like vision and language, is rapidly gaining traction. This enriched data representation improves performance across various tasks. Existing methods for out-of-distribution (OOD) detection, a critical area…

Object detection in remote sensing imagery remains a challenging task due to extreme scale variation, dense object distributions, and cluttered backgrounds. While recent detectors such as YOLOv8 have shown promising results, their backbone…

In recent years, deep learning technology has been maturely applied in the field of object detection, and most algorithms tend to be supervised learning. However, a large amount of labeled data requires high costs of human resources, which…

Domain adaptive object detection (DAOD) assumes that both labeled source data and unlabeled target data are available for training, but this assumption does not always hold in real-world scenarios. Thus, source-free DAOD is proposed to…

Stripe-like space target detection (SSTD) is crucial for space situational awareness. Traditional unsupervised methods often fail in low signal-to-noise ratio and variable stripe-like space targets scenarios, leading to weak generalization.…

The proliferation of Large Language Models (LLMs) in function calling is pivotal for creating advanced AI agents, yet their large scale hinders widespread adoption, necessitating transferring their capabilities into smaller ones. However,…

Clinical 12-lead ECG classification remains difficult because of diverse recording conditions, overlapping pathologies, and pronounced label imbalance hinder generalization, while unconstrained augmentations risk distorting diagnostically…

Unlike popular solutions based on dense feature maps, Object-Centric Learning (OCL) represents visual scenes as sub-symbolic object-level feature vectors, termed slots, which are highly versatile for tasks involving visual modalities. OCL…

Current anchor-free object detectors are quite simple and effective yet lack accurate label assignment methods, which limits their potential in competing with classic anchor-based models that are supported by well-designed assignment…

Deep models trained on a single source domain often fail catastrophically under distribution shifts, a critical challenge in Single Domain Generalization (SDG). While existing methods focus on augmenting source data or learning invariant…

Self-supervised learning systems have gained significant attention in recent years by leveraging clustering-based pseudo-labels to provide supervision without the need for human annotations. However, the noise in these pseudo-labels caused…

Source-free object detection (SFOD) aims to adapt a source-trained detector to an unlabeled target domain without access to the labeled source data. Current SFOD methods utilize a threshold-based pseudo-label approach in the adaptation…

Semi-supervised object detection (SSOD) is a research hot spot in computer vision, which can greatly reduce the requirement for expensive bounding-box annotations. Despite great success, existing progress mainly focuses on two-stage…