English
Related papers

Related papers: Long-tailed Instance Segmentation using Gumbel Opt…

200 papers

Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object categories which limits their applicability in real world…

Computer Vision and Pattern Recognition · Computer Science 2021-03-29 Amirreza Shaban , Amir Rahimi , Thalaiyasingam Ajanthan , Byron Boots , Richard Hartley

3D point cloud semantic segmentation has a wide range of applications. Recently, weakly supervised point cloud segmentation methods have been proposed, aiming to alleviate the expensive and laborious manual annotation process by leveraging…

Computer Vision and Pattern Recognition · Computer Science 2024-01-01 Xiawei Li , Qingyuan Xu , Jing Zhang , Tianyi Zhang , Qian Yu , Lu Sheng , Dong Xu

Existing deepfake detectors face several challenges in achieving robustness and generalization. One of the primary reasons is their limited ability to extract relevant information from forgery videos, especially in the presence of various…

Computer Vision and Pattern Recognition · Computer Science 2023-05-01 Zhiyuan Yan , Peng Sun , Yubo Lang , Shuo Du , Shanzhuo Zhang , Wei Wang , Lei Liu

We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic…

Computer Vision and Pattern Recognition · Computer Science 2017-04-11 Samuel Rota Bulò , Gerhard Neuhold , Peter Kontschieder

Active learning (AL) strategies aim to train high-performance models with minimal labeling efforts, only selecting the most informative instances for annotation. Current approaches to evaluating data informativeness predominantly focus on…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Zhixuan Liang , Xingyu Zeng , Rui Zhao , Ping Luo

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…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Chaowei Fang , Dingwen Zhang , Wen Zheng , Xue Li , Le Yang , Lechao Cheng , Junwei Han

Adaptive optimization methods (such as Adam) play a major role in LLM pretraining, significantly outperforming Gradient Descent (GD). Recent studies have proposed new smoothness assumptions on the loss function to explain the advantages of…

Machine Learning · Computer Science 2025-12-02 Robin Yadav , Shuo Xie , Tianhao Wang , Zhiyuan Li

Balancing training on long-tail data distributions remains a long-standing challenge in deep learning. While methods such as re-weighting and re-sampling help alleviate the imbalance issue, limited sample diversity continues to hinder…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Shizhen Zhao , Xin Wen , Jiahui Liu , Chuofan Ma , Chunfeng Yuan , Xiaojuan Qi

Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors. While class labels naturally follow a long-tailed distribution in the real world, existing benchmarks only focus on a few common classes…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Yechi Ma , Neehar Peri , Achal Dave , Wei Hua , Deva Ramanan , Shu Kong

In the field of pattern classification, the training of deep learning classifiers is mostly end-to-end learning, and the loss function is the constraint on the final output (posterior probability) of the network, so the existence of Softmax…

Computer Vision and Pattern Recognition · Computer Science 2022-10-24 Qiuyu Zhu , Xuewen Zu

Semantic segmentation usually suffers from a long-tail data distribution. Due to the imbalanced number of samples across categories, the features of those tail classes may get squeezed into a narrow area in the feature space. Towards a…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Yuchao Wang , Jingjing Fei , Haochen Wang , Wei Li , Tianpeng Bao , Liwei Wu , Rui Zhao , Yujun Shen

Active learning strategies aim to train high-performance models with minimal labeled data by selecting the most informative instances for labeling. However, existing methods for assessing data informativeness often fail to align directly…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Zhixuan Liang , Xingyu Zeng , Rui Zhao , Ping Luo

Classification on long-tailed distributed data is a challenging problem, which suffers from serious class-imbalance and hence poor performance on tail classes with only a few samples. Owing to this paucity of samples, learning on the tail…

Computation and Language · Computer Science 2022-07-25 Taha ValizadehAslani , Yiwen Shi , Jing Wang , Ping Ren , Yi Zhang , Meng Hu , Liang Zhao , Hualou Liang

A thorough and holistic scene understanding is crucial for autonomous vehicles, where LiDAR semantic segmentation plays an indispensable role. However, most existing methods focus on the network design while neglecting the inherent…

Computer Vision and Pattern Recognition · Computer Science 2021-03-29 Peishan Cong , Xinge Zhu , Yuexin Ma

Gradient clipping is a widely used technique in Machine Learning and Deep Learning (DL), known for its effectiveness in mitigating the impact of heavy-tailed noise, which frequently arises in the training of large language models.…

Optimization and Control · Mathematics 2025-09-30 Savelii Chezhegov , Aleksandr Beznosikov , Samuel Horváth , Eduard Gorbunov

Generative Adversarial Networks (GAN) are a powerful methodology and can be used for unsupervised anomaly detection, where current techniques have limitations such as the accurate detection of anomalies near the tail of a distribution. GANs…

Machine Learning · Computer Science 2022-02-03 Nikolaos Dionelis , Mehrdad Yaghoobi , Sotirios A. Tsaftaris

It is generally accepted that one of the critical parts of current vision algorithms based on deep learning and convolutional neural networks is the annotation of a sufficient number of images to achieve competitive performance. This is…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Kai Yao , Alberto Ortiz , Francisco Bonnin-Pascual

As the data scale grows, deep recognition models often suffer from long-tailed data distributions due to the heavy imbalanced sample number across categories. Indeed, real-world data usually exhibit some similarity relation among different…

Computer Vision and Pattern Recognition · Computer Science 2022-08-18 Lei Liu , Li Liu

The performance of the state-of-the-art image segmentation methods heavily relies on the high-quality annotations, which are not easily affordable, particularly for medical data. To alleviate this limitation, in this study, we propose a…

Machine Learning · Statistics 2019-08-20 Aliasghar Mortazi , Naji Khosravan , Drew A. Torigian , Sila Kurugol , Ulas Bagci

The cross-entropy softmax loss is the primary loss function used to train deep neural networks. On the other hand, the focal loss function has been demonstrated to provide improved performance when there is an imbalance in the number of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Leslie N. Smith