Related papers: Adaptive Logit Adjustment Loss for Long-Tailed Vis…

In the real world, long-tailed data distributions are prevalent, making it challenging for models to effectively learn and classify tail classes. However, we discover that in the field of drug chemistry, certain tail classes exhibit higher…

We propose a simple data model inspired from natural data such as text or images, and use it to study the importance of learning features in order to achieve good generalization. Our data model follows a long-tailed distribution in the…

In recent years, large language models (LLMs) have shown exceptional capabilities across various natural language processing (NLP) tasks. However, such impressive performance often comes with the trade-off of an increased parameter size,…

Multi-modal deep metric learning is crucial for effectively capturing diverse representations in tasks such as face verification, fine-grained object recognition, and product search. Traditional approaches to metric learning, whether based…

Training deep neural networks with noise and data heterogeneity is a major challenge. We introduce Lightweight Learnable Adaptive Weighting (LiLAW), a method that dynamically adjusts the loss weight of each training sample based on its…

Multimodal Large Language Models (MLLMs) have shown strong performance in multi-image cross-modal retrieval, yet suffer from severe position bias, where predictions are dominated by input order rather than semantic relevance. Through…

In medical contexts, the imbalanced data distribution in long-tailed datasets, due to scarce labels for rare diseases, greatly impairs the diagnostic accuracy of deep learning models. Recent multimodal text-image supervised foundation…

Deep neural network training involves both forward propagation (from features through logits to loss) and backward propagation (from loss through gradients to parameter updates). While perturbations along the forward chain, including…

A robot's deployment environment often involves perceptual changes that differ from what it has experienced during training. Standard practices such as data augmentation attempt to bridge this gap by augmenting source images in an effort to…

Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates…

Object detection is a typical multi-task learning application, which optimizes classification and regression simultaneously. However, classification loss always dominates the multi-task loss in anchor-based methods, hampering the consistent…

The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challenges associated with training or fine-tuning these large…

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…

Recently, Miller et al. (2021) and Baek et al. (2022) empirically demonstrated strong linear correlations between in-distribution (ID) versus out-of-distribution (OOD) accuracy and agreement. These trends, coined accuracy-on-the-line (ACL)…

With the development of deep learning, the field of face anti-spoofing (FAS) has witnessed great progress. FAS is usually considered a classification problem, where each class is assumed to contain a single cluster optimized by softmax…

This paper presents an investigation into long-tail video recognition. We demonstrate that, unlike naturally-collected video datasets and existing long-tail image benchmarks, current video benchmarks fall short on multiple long-tailed…

Training a model for food recognition is challenging because the training samples, which are typically crawled from the Internet, are visually different from the pictures captured by users in the free-living environment. In addition to this…

Real-world datasets often exhibit long-tailed distributions, where a few dominant "Head" classes have abundant samples while most "Tail" classes are severely underrepresented, leading to biased learning and poor generalization for the Tail.…

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…

One key challenge in Out-of-Distribution (OOD) detection is the absence of ground-truth OOD samples during training. One principled approach to address this issue is to use samples from external datasets as outliers (i.e., pseudo OOD…