Papers Long-tail Learning
“Long-tail Learning” 태그가 달린 논문 134편 · 필터 해제
Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation
While generalist robot policies hold significant promise for learning diverse manipulation skills through imitation, their performance is often hindered by the long-tail distribution of training demonstrations. Policies …
Long-tail LearningSpatial ReasoningEfficient Long-Tail Learning in Latent Space by sampling Synthetic Data
Imbalanced classification datasets pose significant challenges in machine learning, often leading to biased models that perform poorly on underrepresented classes. With the rise of foundation models, recent research has …
parameter-efficient fine-tuningComputational EfficiencyLong-tail LearningGenerative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model
While data-driven trajectory prediction has enhanced the reliability of autonomous driving systems, it still struggles with rarely observed long-tail scenarios. Prior works addressed this by modifying model architectures…
Trajectory PredictionLong-tail LearningAutonomous DrivingActive LearningMitigating Spurious Correlations with Causal Logit Perturbation
Deep learning has seen widespread success in various domains such as science, industry, and society. However, it is acknowledged that certain approaches suffer from non-robustness, relying on spurious correlations for pr…
counterfactualLong-tail LearningMeta-LearningLIFT+: Lightweight Fine-Tuning for Long-Tail Learning
The fine-tuning paradigm has emerged as a prominent approach for addressing long-tail learning tasks in the era of foundation models. However, the impact of fine-tuning strategies on long-tail learning performance remain…
Data AugmentationLong-tail LearningImproving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
Long-tail learning has garnered widespread attention and achieved significant progress in recent times. However, even with pre-trained prior knowledge, models still exhibit weaker generalization performance on tail class…
Long-tail LearningVisual Prompt TuningLearning from Neighbors: Category Extrapolation for Long-Tail Learning
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 conti…
Long-tail LearningRepresentation LearningContinuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-…
Contrastive LearningDensity EstimationLong-tail LearningAUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance …
Long-tail LearningSemantic SegmentationRepresentation Norm Amplification for Out-of-Distribution Detection in Long-Tail Learning
Detecting out-of-distribution (OOD) samples is a critical task for reliable machine learning. However, it becomes particularly challenging when the models are trained on long-tailed datasets, as the models often struggle…
ClassificationLong-tail LearningOut-of-Distribution DetectionLTRL: Boosting Long-tail Recognition via Reflective Learning
In real-world scenarios, where knowledge distributions exhibit long-tail. Humans manage to master knowledge uniformly across imbalanced distributions, a feat attributed to their diligent practices of reviewing, summarizi…
Long-tail LearningOn Characterizing and Mitigating Imbalances in Multi-Instance Partial Label Learning
*Multi-Instance Partial Label Learning* (MI-PLL) is a weakly-supervised learning setting encompassing *partial label learning*, *latent structural learning*, and *neurosymbolic learning*. Unlike supervised learning, in M…
Long-tail LearningPartial Label LearningWeakly-supervised LearningAdaptive Parametric Activation
The activation function plays a crucial role in model optimisation, yet the optimal choice remains unclear. For example, the Sigmoid activation is the de-facto activation in balanced classification tasks, however, in imb…
imbalanced classificationInstance SegmentationLong-tail LearningEnhanced Long-Tailed Recognition with Contrastive CutMix Augmentation
Real-world data often follows a long-tailed distribution, where a few head classes occupy most of the data and a large number of tail classes only contain very limited samples. In practice, deep models often show poor ge…
Contrastive LearningData AugmentationImage ClassificationLong-tail LearningHarnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be b…
DiversityImage ClassificationLong-tail LearningTest Agnostic Long-Tailed LearningMeta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distribution
Addressing the challenges of rare diseases is difficult, especially with the limited number of reference images and a small patient population. This is more evident in rare skin diseases, where we encounter long-tailed d…
Data AugmentationFew-Shot LearningLong-tail LearningMedical Diagnosis+3Boosting Model Resilience via Implicit Adversarial Data Augmentation
Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains …
Data AugmentationLong-tail LearningMeta-LearningmodelDeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
Vision Transformer (ViT) has emerged as a prominent architecture for various computer vision tasks. In ViT, we divide the input image into patch tokens and process them through a stack of self attention blocks. However, …
Image ClassificationInductive BiasLong-tail LearningProbabilistic Contrastive Learning for Long-Tailed Visual Recognition
Long-tailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples. Such imbalance issue considerably impairs the performance of standard super…
Long-tail LearningSURE: SUrvey REcipes for building reliable and robust deep networks
In this paper, we revisit techniques for uncertainty estimation within deep neural networks and consolidate a suite of techniques to enhance their reliability. Our investigation reveals that an integrated application of …
image-classificationImage ClassificationLearning with noisy labelsLong-tail Learning+1