Long-tailed Object Detection
16 papers with code • 1 benchmarks • 1 datasets
The training dataset obeys a long-tailed distribution, i.e., the head categories occupy most samples whereas the tail categories only own a few samples. However, the testing dataset is balanced across categories.
Most implemented papers
Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection
To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally.
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation
In the classification tree, as the number of parent class nodes are significantly less, their logits are less noisy and can be utilized to suppress the wrong/noisy logits existed in the fine-grained class nodes.
Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection
To this end, we rethink long-tailed object detection in UAV images and propose the Dual Sampler and Head detection Network (DSHNet), which is the first work that aims to resolve long-tail distribution in UAV images.
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
Many objects do not appear frequently enough in complex scenes (e. g., certain handbags in living rooms) for training an accurate object detector, but are often found frequently by themselves (e. g., in product images).
On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
We propose NorCal, Normalized Calibration for long-tailed object detection and instance segmentation, a simple and straightforward recipe that reweighs the predicted scores of each class by its training sample size.
Exploring Classification Equilibrium in Long-Tailed Object Detection
Specifically, EBL increases the intensity of the adjustment of the decision boundary for the weak classes by a designed score-guided loss margin between any two classes.
Equalized Focal Loss for Dense Long-Tailed Object Detection
The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem.
Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning
Specifically, there are an object detection task (consisting of an instance-classification task and a localization task) and an image-classification task in our framework, responsible for utilizing the two types of supervision.
The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
Long-tail distribution is widely spread in real-world applications.
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.