Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
Awesome-LongTailed-Learning
A codebase and a curated list of awesome deep long-tailed learning (TPAMI 2023).
https://github.com/Vanint/Awesome-LongTailed-Learning
Last synced: 1 day ago
JSON representation
-
2. Top-tier Conference Papers (Updated on 2024 November)
-
2021
- Self supervision to distillation for long-tailed visual recognition - NJU/SSD-LT) |
- Parametric contrastive learning - research/Parametric-Contrastive-Learning) |
- Learning of visual relations: The devil is in the tails
- Improving contrastive learning on imbalanced seed data via open-world sampling - Group/MAK) |
- Exploring classification equilibrium in long-tailed object detection
- Re-distributing biased pseudo labels for semi-supervised semantic segmentation: A baseline investigation - Lab/DARS) |
- MosaicOS: A simple and effective use of object-centric images for long-tailed object detection
- Delving into deep imbalanced regression - regression) |
- PML: Progressive margin loss for long-tailed age classification
- Distribution alignment: A unified framework for long-tail visual recognition - BaseDetection/DisAlign) |
- Improving calibration for long-tailed recognition - research/MiSLAS) |
- Unsupervised discovery of the long-tail in instance segmentation using hierarchical self-supervision
- Long-tailed recognition by routing diverse distribution-aware experts - xwang/RIDE-LongTailRecognition) |
- VideoLT: Large-scale long-tailed video recognition
- ACE: Ally complementary experts for solving long-tailed recognition in one-shot
- Self-Damaging Contrastive Learning - Group/SDCLR) |
- Semi-supervised semantic segmentation via adaptive equalization learning - AEL) |
- On model calibration for long-tailed object detection and instance segmentation
- Label-imbalanced and group-sensitive classification under overparameterization
- Towards calibrated model for long-tailed visual recognition from prior perspective - LT) |
- Supercharging imbalanced data learning with energy-based contrastive representation transfer
- FASA: Feature augmentation and sampling adaptation for long-tailed instance segmentation
- Influence-Balanced Loss for Imbalanced Visual Classification - Loss) |
- Distilling virtual examples for long-tailed recognition
- Distributional robustness loss for long-tail learning - LT) |
- Long-tailed multi-label visual recognition by collaborative training on uniform and re-balanced samplings
- Equalization loss v2: A new gradient balance approach for long-tailed object detection
- Seesaw loss for long-tailed instance segmentation - mmlab/mmdetection) |
- Adaptive class suppression loss for long-tail object detection - IVA-Lab/ACSL) |
- Disentangling label distribution for long-tailed visual recognition
- Adversarial robustness under long-tailed distribution - Tail) |
- CReST: A class-rebalancing self-training framework for imbalanced semi-supervised learning - research/crest) |
- Conceptual 12M: Pushing web-scale image-text pre-training to recognize long-tail visual concepts - research-datasets/conceptual-12m) |
- RSG: A simple but effective module for learning imbalanced datasets - Wang/RSG) |
- MetaSAug: Meta semantic augmentation for long-tailed visual recognition - DA/MetaSAug) |
- Contrastive learning based hybrid networks for long-tailed image classification
- Long-tail learning via logit adjustment - research/google-research/tree/master/logit_adjustment) |
- Exploring balanced feature spaces for representation learning
- GistNet: a geometric structure transfer network for long-tailed recognition
- Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
-
2024
- Taming the long tail in human mobility prediction
- Long-tailed object detection pre-training: dynamic rebalancing contrastive learning with dual reconstruction
- AUCSeg: AUC-oriented pixel-level long-tail semantic segmentation
- Continuous contrastive learning for long-tailed semi-supervised recognition
- Long-tailed out-of-distribution detection via normalized outlier distribution adaptation - lab/AdaptOD) |
- LLM-ESR: Large language models enhancement for long-tailed sequential recommendation - Machine-Learning-Lab/LLM-ESR) |
- DiffuLT: Diffusion for long-tail recognition without external knowledge
- LLM-AutoDA: Large language model-driven automatic data augmentation for long-tailed problems - atom/LLM-LT-AUG) |
- Breaking long-tailed learning bottlenecks: A controllable paradigm with hypernetwork-generated diverse experts - atom/PRL) |
- Once Read is Enough: Domain-specific pretraining-free language models with cluster-guided sparse experts for long-tail domain knowledge
- Improving visual prompt tuning by Gaussian neighborhood minimization for long-tailed visual recognition - PT) |
- Towards heterogeneous long-tailed learning: Benchmarking, Metrics, and Toolbox
- What makes CLIP more robust to long-tailed pre-training data? A controlled study for transferable insights - Lab/clip-beyond-tail) |
- Flexible distribution alignment: Towards long-tailed semi-supervised learning with proper calibration - LTSSL) |
- Long-tail temporal action segmentation with group-wise temporal logit adjustment
- Distribution-aware robust learning from long-tailed data with noisy labels
- Distributionally robust loss for long-tailed multi-label image classification - Loss) |
- Rectify the regression bias in long-tailed object detection
- LTRL: Boosting long-tail recognition via reflective learning
- Learning label shift correction for test-agnostic long-tailed recognition - ache/label-shift-correction) |
- Generative active learning for long-tailed instance segmentation
- ELTA: An enhancer against long-tail for aesthetics-oriented models - Tail-image-aesthetics-and-quality-assessment) |
- Distribution alignment optimization through neural collapse for long-tailed classification
- Long-tail learning with foundation model: Heavy fine-tuning hurts
- SimPro: A simple probabilistic framework towards realistic long-tailed semi-supervised learning
- Harnessing hierarchical label distribution variations in test agnostic long-tail recognition
- Two Fists, One Heart: Multi-objective optimization based strategy fusion for long-tailed learning - atom/torch-MOOSF) |
- BEM: Balanced and entropy-based mix for long-tailed semi-supervised learning - BEM) |
- DeiT-LT: Distillation strikes back for vision transformer training on long-tailed datasets - iisc/DeiT-LT) |
- Revisiting adversarial training under long-tailed distributions - BSL) |
- Long-tailed anomaly detection with learnable class names
- LTGC: Long-tail recognition via leveraging LLMs-driven generated content
- Delving into the trajectory long-tail distribution for multi-object tracking - si-jia/Trajectory-Long-tail-Distribution-for-MOT) |
- Long-tail class incremental learning via independent sub-prototype construction
- Long-tailed diffusion models with oriented calibration - SJTU/OC_LT) |
- Kill two birds with one stone: Rethinking data augmentation for deep long-tailed learning - for-DODA) |
- FedLoGe: Joint local and generic federated learning under long-tailed data
- Learning to reject meets long-tail learning
- Exploring weight balancing on long-tailed recognition problem - Weight-Balancing-on-Long-Tailed-Recognition-Problem) |
- Pareto deep long-tailed recognition: A conflict-averse solution
-
2023
- AREA: Adaptive reweighting via effective area for long-tailed classification - chen/AREA) |
- Reconciling object-level and global-level objectives for long-tail detection
- Local and global logit adjustments for long-tailed learning
- Learning in imperfect environment: Multi-label classification with long-tailed distribution and partial labels
- Global balanced experts for federated long-tailed learning - Long-tailed-Learning) |
- Boosting long-tailed object detection via step-wise learning on smooth-tail data
- Long-tailed recognition by mutual information maximization between latent features and ground-truth labels - tailed-recognition) |
- How re-sampling helps for long-tail learning?
- Fed-GraB: Federated long-tailed learning with self-adjusting gradient balancer
- Enhancing minority classes by mixing: an adaptative optimal transport approach for long-tailed classification - Minority-Classes-by-Mixing) |
- Learning from rich semantics and coarse locations for long-tailed object detection
- Generalized test utilities for long-tail performance in extreme multi-label classification
- Label-noise learning with intrinsically long-tailed data
- MDCS: More diverse experts with consistency self-distillation for long-tailed recognition
- Subclass-balancing Contrastive Learning for Long-tailed Recognition
- When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method
- Transfer knowledge from head to tail: Uncertainty calibration under long-tailed distribution
- Towards realistic long-tailed semi-supervised learning: Consistency is all you need
- Global and local mixture consistency cumulative learning for long-tailed visual recognitions - yangpeng/GLMC) |
- FEND: A future enhanced distribution-aware contrastive learning framework for long-tail trajectory prediction
- No one left behind: Improving the worst categories in long-tailed learning
- On the effectiveness of out-of-distribution data in self-supervised long-tail learning
- Large language models struggle to learn long-tail knowledge
- Feature directions matter: Long-tailed learning via rotated balanced representation
- Wrapped Cauchy distributed angular softmax for long-tailed visual recognition
- Rethinking image super resolution from long-tailed distribution learning perspective
- Long-tailed visual recognition via self-heterogeneous integration with knowledge excavation - 06/SHIKE) |
- Balancing logit variation for long-tailed semantic segmentation
- Use your head: Improving long-tail video recognition
- FCC: Feature clusters compression for long-tailed visual recognition
- SuperDisco: Super-class discovery improves visual recognition for the long-tail
- Class-conditional sharpness-aware minimization for deep long-tailed recognition - SAM) |
- Balanced product of calibrated experts for long-tailed recognition - CalibratedLT) |
- LPT: Long-tailed prompt tuning for image classification
- Long-tailed partial label learning via dynamic rebalancing - SJTU/RECORDS-LTPLL) |
- Delving into semantic scale imbalance
- INPL: Pseudo-labeling the inliers first for imbalanced semi-supervised learning
- CUDA: Curriculum of data augmentation for long-tailed recognition
- Long-tailed learning requires feature learning
- Decoupled training for long-tailed classification with stochastic representations
-
2022
- Self-supervised aggregation of diverse experts for test-agnostic long-tailed recognition - AgnosticLT) |
- Identifying hard noise in long-tailed sample distribution - Framework) |
- Relieving long-tailed instance segmentation via pairwise class balance - research/PCB) |
- Nested collaborative learning for long-tailed visual recognition
- Killing two birds with one stone: Efficient and robust training of face recognition CNNs by partial FC
- Do deep networks transfer invariances across classes? - invariance-transfer) |
- Long-tail recognition via compositional knowledge transfer
- Long-tailed recognition via weight balancing - weight-balancing) |
- SoLar: Sinkhorn label refinery for imbalanced partial-label learning
- Do we really need a learnable classifier at the end of deep neural network?
- Maximum class separation as inductive bias in one matrix - separation-as-inductive-bias) | |
- Escaping saddle points for effective generalization on class-imbalanced data - iisc/Saddle-LongTail) | |
- Breadcrumbs: Adversarial class-balanced sampling for long-tailed recognition - SVCL/Breadcrumbs) |
- Constructing balance from imbalance for long-tailed image recognition
- Tackling long-tailed category distribution under domain shifts - ds) |
- Improving GANs for long-tailed data through group spectral regularization - iisc/gSRGAN) |
- Learning class-wise visual-linguistic representation for long-tailed visual recognition - LTR) |
- Learning with free object segments for long-tailed instance segmentation
- SAFA: Sample-adaptive feature augmentation for long-tailed image classification
- On multi-domain long-tailed recognition, imbalanced domain generalization, and beyond - domain-imbalance) |
- Invariant feature learning for generalized long-tailed classification - Long-Tailed-Benchmarks.pytorch) |
- Towards calibrated hyper-sphere representation via distribution overlap coefficient for long-tailed learning - OP) |
- Long-tailed instance segmentation using Gumbel optimized loss
- Long-tailed class incremental learning - Tailed-CIL) |
- The majority can help the minority: Context-rich minority oversampling for long-tailed classification - ai/cmo) |
- Class-balanced pixel-level self-labeling for domain adaptive semantic segmentation
- Optimal transport for long-tailed recognition with learnable cost matrix
- Self-supervised learning is more robust to dataset imbalance
- BatchFormer: Learning to explore sample relationships for robust representation learning
-
2020
- Long-tailed classification by keeping the good and removing the bad momentum causal effect - Tailed-Recognition.pytorch) |
- Distribution-balanced loss for multi-label classification in long-tailed datasets
- BBN: Bilateral-branch network with cumulative learning for long-tailed visual recognition - Nanjing/BBN) |
- Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective
- Balanced meta-softmax for long-taield visual recognition - ren/BalancedMetaSoftmax) |
- Posterior recalibration for imbalanced datasets - RIPL/UNO-IC) |
- Rethinking the value of labels for improving classimbalanced learning - semi-self) |
- The devil is in classification: A simple framework for long-tail instance segmentation
- Imbalanced continual learning with partitioning reservoir sampling
- Feature space augmentation for long-tailed data
- Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification
- Solving long-tailed recognition with deep realistic taxonomic classifier - RTC) |
- Learning to segment the tail
- Overcoming classifier imbalance for long-tail object detection with balanced group softmax
- Equalization loss for long-tailed object recognition
- Domain balancing: Face recognition on long-tailed domains
- M2m: Imbalanced classification via majorto-minor translation
- Deep representation learning on long-tailed data: A learnable embedding augmentation perspective
- Inflated episodic memory with region self-attention for long-tailed visual recognition
- Decoupling representation and classifier for long-tailed recognition - balancing) |
-
2019
- Striking the right balance with uncertainty
- Feature transfer learning for face recognition with under-represented data
- Meta-weight-net: Learning an explicit mapping for sample weighting - weight-net) |
- Learning imbalanced datasets with label-distribution-aware margin loss - DRW) |
- Dynamic curriculum learning for imbalanced data classification
- Class-balanced loss based on effective number of samples - balanced-loss) |
- Unequal-training for deep face recognition with long-tailed noisy data - Training-for-Deep-Face-Recognition-with-Long-Tailed-Noisy-Data) |
- Large-scale long-tailed recognition in an open world - OLTR) |
-
2018
- Large scale fine-grained categorization and domain-specific transfer learning - inaturalist-transfer) |
-
2017
-
2016
-
-
Star History
-
(2) More discussions on cost-sensitive losses
- ![Star History Chart - history.com/#Vanint/Awesome-LongTailed-Learning&Timeline)
- ![Star History Chart - history.com/#Vanint/Awesome-LongTailed-Learning&Timeline)
-
-
5. Other Resources
-
(2) More discussions on cost-sensitive losses
-
-
2. Top-tier Conference Papers
-
2022
- Relieving long-tailed instance segmentation via pairwise class balance - research/PCB) |
- Long-tail recognition via compositional knowledge transfer
- BatchFormer: Learning to explore sample relationships for robust representation learning
- Nested collaborative learning for long-tailed visual recognition
- Long-tailed recognition via weight balancing - weight-balancing) |
-
2021
- VideoLT: Large-scale long-tailed video recognition
- GistNet: a geometric structure transfer network for long-tailed recognition
- ACE: Ally complementary experts for solving long-tailed recognition in one-shot
- Self supervision to distillation for long-tailed visual recognition - NJU/SSD-LT) |
- MosaicOS: A simple and effective use of object-centric images for long-tailed object detection
- Parametric contrastive learning - research/Parametric-Contrastive-Learning) |
- Learning of visual relations: The devil is in the tails
- Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
- Self-Damaging Contrastive Learning - Group/SDCLR) |
- Delving into deep imbalanced regression - regression) |
-
Programming Languages
Categories
Sub Categories