Pith. sign in

REVIEW 16 cited by

Long-tail learning via logit adjustment

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2007.07314 v2 pith:XPXSDIBO submitted 2020-07-14 cs.LG stat.ML

classification cs.LGstat.ML
keywords labelsadjustmentdominantlabellearninglogittechniquestraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Real-world classification problems typically exhibit an imbalanced or long-tailed label distribution, wherein many labels are associated with only a few samples. This poses a challenge for generalisation on such labels, and also makes na\"ive learning biased towards dominant labels. In this paper, we present two simple modifications of standard softmax cross-entropy training to cope with these challenges. Our techniques revisit the classic idea of logit adjustment based on the label frequencies, either applied post-hoc to a trained model, or enforced in the loss during training. Such adjustment encourages a large relative margin between logits of rare versus dominant labels. These techniques unify and generalise several recent proposals in the literature, while possessing firmer statistical grounding and empirical performance.

Discussion (0). Sign in to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Recurrent Contrastive Learning for Imbalanced Medical Image Classification

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A recurrent contrastive learning framework with temporal memory queues and anchors improves balanced accuracy for imbalanced medical image classification.

  2. From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Sharpness-Guided Equilibrium Sampling reweights long-tailed training batches using cumulative class counts and SAM perturbation-loss gaps, improving tail accuracy by up to 10.8 points.

  3. Loss Landscape Topology Reveals Why Simple Baselines are Competitive at 3D Point Cloud Segmentation Under Class Imbalance

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Uniform cross-entropy is competitive with 11 imbalance-aware losses in point-based 3D segmentation; specialized methods give small, architecture-dependent gains.

  4. Revisiting Scene Graph Generation from the Perspective of Detector-Conditioned Reachability

    cs.CV 2026-07 accept novelty 6.0 of 10

    A dual-query scene graph generation method unifies detector-based and query-based reasoning in a single decoder, achieving state-of-the-art results on Visual Genome, Open Images v6, and GQA-200.

  5. Generative Distribution Distillation

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Knowledge distillation is reformulated as conditional diffusion over teacher feature tokens, with class-center contraction replacing the classification loss, yielding state-of-the-art ImageNet distillation numbers.

  6. MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Pairing high-difficulty with low-difficulty images, ranked by loss and uncertainty, makes minibatch training more effective and improves accuracy on four computer vision tasks.

  7. Mutually Exclusive Multiclass Lesion Segmentation in Neuroimaging: Binary-Guided Weak Supervision with Inter-Class Orthogonality

    eess.IV 2026-07 accept novelty 5.0 of 10

    Binary-guided mutual exclusivity with inter-class orthogonality yields accurate multiclass weakly supervised neuroimaging lesion segmentation from image-level labels alone.

  8. SciLT: Long-tailed Image Classification under Scientific Image Domains

    cs.CV 2026-04 conditional novelty 5.0 of 10

    On scientific long-tailed image tasks, foundation-model fine-tuning gains are limited; SciLT fuses penultimate and final ViT features under dual supervision to improve balanced accuracy.

  9. Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts

    cs.LG 2025-07 conditional novelty 5.0 of 10

    DCE trains frequency-aware experts with complementary losses plus a Gaussian-sampled dynamic selector, reporting SOTA accuracy on four imbalanced domain-incremental benchmarks.

  10. Mixture Experts with Test-Time Self-Supervised Aggregation for Tabular Imbalanced Regression

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A mixture-of-experts model with test-time self-supervised weight adjustment improves tabular imbalanced regression under three different test distributions, reporting a 7.1% average MAE gain.

  11. Tuning the Right Foundation Models is What you Need for Partial Label Learning

    cs.LG 2025-06 conditional novelty 5.0 of 10

    Fine-tuning foundation models such as CLIP gives large, robust gains in partial label learning and makes the choice of PLL algorithm nearly irrelevant.

  12. Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A two-stage diffusion-based data augmentation pipeline with confusing-class negative prompts improves long-tailed food image classification accuracy on Food101-LT and VFN-LT.

  13. Aligned Contrastive Loss for Long-Tailed Recognition

    cs.CV 2025-06 conditional novelty 5.0 of 10

    ACL modifies supervised contrastive loss by removing non-effective positives from the denominator, adding class centers, and re-weighting negatives by inverse class frequency, yielding new state-of-the-art accuracy on...

  14. Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition

    cs.CV 2025-09 conditional novelty 4.0 of 10

    A balanced information bottleneck loss, extended to a mixture over intermediate layers, improves reported accuracy on three long-tailed visual recognition benchmarks.

  15. Subtyping Breast Lesions via Generative Augmentation based Long-tailed Recognition in Ultrasound

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A dual-phase framework with a sketch-guided diffusion synthesizer and an RL-based adaptive sampler improves long-tailed breast ultrasound subtype classification over the tested baselines.

  16. Learning from Limited and Imperfect Data

    cs.LG 2025-07 unverdicted novelty 3.0 of 10

    A doctoral thesis compiling nine peer-reviewed papers on long-tailed image generation, long-tailed recognition, semi-supervised learning, and domain adaptation.

Pith tools