Related papers: Balanced Representation Learning for Long-tailed S…
In conventional deep learning, the number of neurons typically remains fixed during training. However, insights from biology suggest that the human hippocampus undergoes continuous neuron generation and pruning of neurons over the course of…
Class imbalance is a common problem in the case of real-world object detection and classification tasks. Data of some classes is abundant making them an over-represented majority, and data of other classes is scarce, making them an…
Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail classes. Existing methods usually modify the classification loss to increase the learning focus on tail classes, which unexpectedly sacrifice the…
Our work focuses on tackling the challenging but natural visual recognition task of long-tailed data distribution (i.e., a few classes occupy most of the data, while most classes have rarely few samples). In the literature, class…
Self-supervised learning (SSL) as an effective paradigm of representation learning has achieved tremendous success on various curated datasets in diverse scenarios. Nevertheless, when facing the long-tailed distribution in real-world…
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…
In vision domain, large-scale natural datasets typically exhibit long-tailed distribution which has large class imbalance between head and tail classes. This distribution poses difficulty in learning good representations for tail classes.…
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…
Convolutional neural networks have achieved great improvement on face recognition in recent years because of its extraordinary ability in learning discriminative features of people with different identities. To train such a well-designed…
Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative…
While current skeleton action recognition models demonstrate impressive performance on large-scale datasets, their adaptation to new application scenarios remains challenging. These challenges are particularly pronounced when facing new…
Skeleton-based human action recognition has attracted increasing attention in recent years. However, most of the existing works focus on supervised learning which requiring a large number of annotated action sequences that are often…
Temporal action segmentation in untrimmed procedural videos aims to densely label frames into action classes. These videos inherently exhibit long-tailed distributions, where actions vary widely in frequency and duration. In temporal action…
Recently, multimodal tasks have strongly advanced the field of action recognition with their rich multimodal information. However, due to the scarcity of tri-modal data, research on tri-modal action recognition tasks faces many challenges.…
In this work, we introduce a novel strategy for long-tail recognition that addresses the tail classes' few-shot problem via training-free knowledge transfer. Our objective is to transfer knowledge acquired from information-rich common…
In this work, we propose an ensemble modeling approach for multimodal action recognition. We independently train individual modality models using a variant of focal loss tailored to handle the long-tailed distribution of the MECCANO [21]…
Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads…
Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to…
Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class…
One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action…