Related papers: Dynamic Class Queue for Large Scale Face Recogniti…
Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples. While existing supervised learning approaches have been…
Despite recent advances in face recognition using deep learning, severe accuracy drops are observed for large pose variations in unconstrained environments. Learning pose-invariant features is one solution, but needs expensively labeled…
Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively in a data privacy-preserving manner. However, the data samples usually follow a long-tailed…
This is a technical report for CVPR 2021 AliProducts Challenge. AliProducts Challenge is a competition proposed for studying the large-scale and fine-grained commodity image recognition problem encountered by worldleading ecommerce…
We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence. In particular, we consider the task setting of incremental learning with limited memory and aim to achieve better…
Deep neural networks suffer from catastrophic forgetting when continually learning new concepts. In this paper, we analyze this problem from a data imbalance point of view. We argue that the imbalance between old task and new task data…
Face verification is a problem approached in the literature mainly using nonlinear class-specific subspace learning techniques. While it has been shown that kernel-based Class-Specific Discriminant Analysis is able to provide excellent…
Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model…
We propose a novel 3D face recognition algorithm using a deep convolutional neural network (DCNN) and a 3D augmentation technique. The performance of 2D face recognition algorithms has significantly increased by leveraging the…
Curriculum learning strategies in prior multi-task learning approaches arrange datasets in a difficulty hierarchy either based on human perception or by exhaustively searching the optimal arrangement. However, human perception of difficulty…
The state of the art of many learning tasks, e.g., image classification, is advanced by collecting larger datasets and then training larger models on them. As the outcome, the increasing computational cost is becoming unaffordable. In this…
Several factors contribute to the appearance of an object in a visual scene, including pose, illumination, and deformation, among others. Each factor accounts for a source of variability in the data, while the multiplicative interactions of…
Automatic snake species recognition is important because it has vast potential to help lower deaths and disabilities caused by snakebites. We introduce our solution in SnakeCLEF 2022 for fine-grained snake species recognition on a heavy…
Long-tailed distributions in class-imbalanced data present a fundamental challenge for deep learning models, which tend to be biased toward majority classes. While recent methods for long-tailed recognition have mitigated this issue, they…
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…
Class imbalance and noisy labels are the norm rather than the exception in many large-scale classification datasets. Nevertheless, most works in machine learning typically assume balanced and clean data. There have been some recent attempts…
We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. The framework not only allows to learn…
Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural networks, which is crucial for model deployment on…
Self-supervised methods based on contrastive learning have achieved great success in unsupervised visual representation learning. However, most methods under this framework suffer from the problem of false negative samples. Inspired by the…
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…