Related papers: Learning Prototype Classifiers for Long-Tailed Rec…

Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle…

Face representation learning using datasets with a massive number of identities requires appropriate training methods. Softmax-based approach, currently the state-of-the-art in face recognition, in its usual "full softmax" form is not…

Fine-tuned pre-trained language models (PLMs) have achieved awesome performance on almost all NLP tasks. By using additional prompts to fine-tune PLMs, we can further stimulate the rich knowledge distributed in PLMs to better serve…

Deep learning algorithms face great challenges with long-tailed data distribution which, however, is quite a common case in real-world scenarios. Previous methods tackle the problem from either the aspect of input space (re-sampling classes…

Long-tailed visual recognition has received increasing attention in recent years. Due to the extremely imbalanced data distribution in long-tailed learning, the learning process shows great uncertainties. For example, the predictions of…

As most ''in the wild'' data collections of the natural world, the North America Camera Trap Images (NACTI) dataset shows severe long-tailed class imbalance, noting that the largest 'Head' class alone covers >50% of the 3.7M images in the…

The imbalance (or long-tail) is the nature of many real-world data distributions, which often induces the undesirable bias of deep classification models toward frequent classes, resulting in poor performance for tail classes. In this paper,…

Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance…

How to estimate the uncertainty of a given model is a crucial problem. Current calibration techniques treat different classes equally and thus implicitly assume that the distribution of training data is balanced, but ignore the fact that…

This paper presents a novel deep learning architecture to classify structured objects in datasets with a large number of visually similar categories. We model sequences of images as linear-chain CRFs, and jointly learn the parameters from…

Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions. To…

Real-world data often exhibits a long-tailed distribution, in which head classes occupy most of the data, while tail classes only have very few samples. Models trained on long-tailed datasets have poor adaptability to tail classes and the…

As a safety critical task, autonomous driving requires accurate predictions of road users' future trajectories for safe motion planning, particularly under challenging conditions. Yet, many recent deep learning methods suffer from a…

Aiming to enhance the utilization of metric space by the parametric softmax classifier, recent studies suggest replacing it with a non-parametric alternative. Although a non-parametric classifier may provide better metric space utilization,…

Deep neural networks often degrade significantly when training data suffer from class imbalance problems. Existing approaches, e.g., re-sampling and re-weighting, commonly address this issue by rearranging the label distribution of training…

We introduce LPT++, a comprehensive framework for long-tailed classification that combines parameter-efficient fine-tuning (PEFT) with a learnable model ensemble. LPT++ enhances frozen Vision Transformers (ViTs) through the integration of…

Existing out-of-distribution (OOD) methods have shown great success on balanced datasets but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples are often wrongly classified into head classes and/or 2)…

The long-tailed distribution datasets poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions usually involve class-balacing strategies or transfer learing from…

A dramatic increase in real-world video volume with extremely diverse and emerging topics naturally forms a long-tailed video distribution in terms of their categories, and it spotlights the need for Video Long-Tailed Recognition (VLTR). In…

Long-tailed multi-label visual recognition (LTML) task is a highly challenging task due to the label co-occurrence and imbalanced data distribution. In this work, we propose a unified framework for LTML, namely prompt tuning with…