Related papers: EHSOD: CAM-Guided End-to-end Hybrid-Supervised Obj…

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD…

Applying pseudo labeling techniques has been found to be advantageous in semi-supervised 3D object detection (SSOD) in Bird's-Eye-View (BEV) for autonomous driving, particularly where labeled data is limited. In the literature, Exponential…

Scene understanding includes many related sub-tasks, such as scene categorization, depth estimation, object detection, etc. Each of these sub-tasks is often notoriously hard, and state-of-the-art classifiers already exist for many of them.…

Recently, sparsely-supervised 3D object detection has gained great attention, achieving performance close to fully-supervised 3D objectors while requiring only a few annotated instances. Nevertheless, these methods suffer challenges when…

We propose a hybrid framework for consistently producing high-quality object tracks by combining an automated object tracker with little human input. The key idea is to tailor a module for each dataset to intelligently decide when an object…

Weakly-supervised object detection (WSOD) has emerged as an inspiring recent topic to avoid expensive instance-level object annotations. However, the bounding boxes of most existing WSOD methods are mainly determined by precomputed…

The unsupervised pretraining of object detectors has recently become a key component of object detector training, as it leads to improved performance and faster convergence during the supervised fine-tuning stage. Existing unsupervised…

Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources while maintaining data privacy. Nevertheless, it faces challenges with limited high-quality labels and non-IID client data,…

Reliable pseudo-labels from unlabeled data play a key role in semi-supervised object detection (SSOD). However, the state-of-the-art SSOD methods all rely on pseudo-labels with high confidence, which ignore valuable pseudo-labels with lower…

Semi-supervised 3D object detection from point cloud aims to train a detector with a small number of labeled data and a large number of unlabeled data. The core of existing methods lies in how to select high-quality pseudo-labels using the…

In this paper, we delve into semi-supervised object detection where unlabeled images are leveraged to break through the upper bound of fully-supervised object detection models. Previous semi-supervised methods based on pseudo labels are…

This study delves into semi-supervised object detection (SSOD) to improve detector performance with additional unlabeled data. State-of-the-art SSOD performance has been achieved recently by self-training, in which training supervision…

To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common techniques to improve the efficacy of such systems in new…

Visually detecting camouflaged objects is a hard problem for both humans and computer vision algorithms. Strong similarities between object and background appearance make the task significantly more challenging than traditional object…

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the problem of training an…

Pseudo-supervised learning methods have been shown to be effective for weakly supervised object localization tasks. However, the effectiveness depends on the powerful regularization ability of deep neural networks. Based on the assumption…

Few-shot object detection(FSOD) aims to design methods to adapt object detectors efficiently with only few annotated samples. Fine-tuning has been shown to be an effective and practical approach. However, previous works often take the…

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless,…

Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant…

Task inharmony problem commonly occurs in modern object detectors, leading to inconsistent qualities between classification and regression tasks. The predicted boxes with high classification scores but poor localization positions or low…