Related papers: Long-Tailed Object Detection Pre-training: Dynamic…
Recently, long-tailed image classification harvests lots of research attention, since the data distribution is long-tailed in many real-world situations. Piles of algorithms are devised to address the data imbalance problem by biasing the…
Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of…
Real-world imagery is often characterized by a significant imbalance of the number of images per class, leading to long-tailed distributions. An effective and simple approach to long-tailed visual recognition is to learn feature…
Scene Graph Generation (SGG) as a critical task in image understanding, facing the challenge of head-biased prediction caused by the long-tail distribution of predicates. However, current unbiased SGG methods can easily prioritize improving…
The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model. In this work, we propose a new method, Gradual Balanced Loss and Adaptive Feature Generator (GLAG) to alleviate imbalance. GLAG…
Deep neural networks still struggle on long-tailed image datasets, and one of the reasons is that the imbalance of training data across categories leads to the imbalance of trained model parameters. Motivated by the empirical findings that…
Although contrastive learning methods have shown prevailing performance on a variety of representation learning tasks, they encounter difficulty when the training dataset is long-tailed. Many researchers have combined contrastive learning…
Long-tailed classification is challenging due to its heavy imbalance in class probabilities. While existing methods often focus on overall accuracy or accuracy for tail classes, they overlook a critical aspect: certain types of errors can…
Accurately predicting the future trajectories of traffic agents is essential in autonomous driving. However, due to the inherent imbalance in trajectory distributions, tail data in natural datasets often represents more complex and…
Most of object detection algorithms can be categorized into two classes: two-stage detectors and one-stage detectors. Recently, many efforts have been devoted to one-stage detectors for the simple yet effective architecture. Different from…
Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO. They tend to suffer performance drop on realistic datasets…
In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to bias on high-frequency classes and thus increases the…
Vanilla models for object detection and instance segmentation suffer from the heavy bias toward detecting frequent objects in the long-tailed setting. Existing methods address this issue mostly during training, e.g., by re-sampling or…
Cross-Domain Detection (XDD) aims to train an object detector using labeled image from a source domain but have good performance in the target domain with only unlabeled images. Existing approaches achieve this either by aligning the…
Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data. We propose a "divide&conquer" strategy for the challenging LVIS task: divide the whole data into balanced parts and then apply…
Dynamic facial expression recognition (DFER) faces significant challenges due to long-tailed category distributions and complexity of spatio-temporal feature modeling. While existing deep learning-based methods have improved DFER…
It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing…
Relational Deep Learning (RDL) is an emerging paradigm that leverages Graph Neural Network principles to learn directly from relational databases by representing them as heterogeneous graphs. However, existing RDL models typically rely on…
Medical image classification has been widely adopted in medical image analysis. However, due to the difficulty of collecting and labeling data in the medical area, medical image datasets are usually highly-imbalanced. To address this…
Long-tailed classification poses a challenge due to its heavy imbalance in class probabilities and tail-sensitivity risks with asymmetric misprediction costs. Recent attempts have used re-balancing loss and ensemble methods, but they are…