Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training

• URL: http://arxiv.org/abs/2608.09688v1
• Date: Mon, 10 Aug 2026 14:54:00 GMT
• Title: Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training
• Abstract summary: Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes.<n>We propose a Confusion Geometry Rebalancing method (CGRm) for long tail adversarial training, a plug in framework that leverages directed robust errors as training signals.
• Score: 53.3522202888031
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias. Existing methods mitigate this issue by correcting class priors or adapting class wise robust supervision, yet they treat each class in isolation and fail to identify which boundaries drive long tailed collapse. We propose a Confusion Geometry Rebalancing method (CGRm) for long tail adversarial training, a plug in framework that leverages directed robust errors as training signals. CGRm leverages periodic robust evaluations to derive source class loss weights, class wise robust coefficients, and a directed confusion geometry graph. The method then couples feedback weighted robust optimization with graph guided margin correction, thereby boosting the robustness of vulnerable classes and sharpening the critical boundaries that drive long tailed performance degradation. Experiments on long tailed benchmarks show that CGRm achieves consistent robust performance gains over existing methods, with ablations validating the contribution of each component. We provide the code in the supplement.

Related papers

• Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration [61.46060073417047]
  Multi-Token Prediction (MTP) has been a widely adopted module in pretraining.<n>We show that the per-step effect of MTP on the RL objective can be decomposed into two terms: a first-order correlation and a second-order penalty.<n>We propose an adaptive scheme that tracks the optimal coefficient online via a log-probability proxy at negligible cost.
  arXiv  Detail & Related papers  (2026-05-27T09:07:06Z)
• Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping [66.25536973294726]
  Post-training methods for text-to-image (T2I) models are prone to reward hacking.<n>Super-Linear Advantage Shaping (SLAS) reshapes the local policy space.<n>SLAS consistently surpasses the DanceGRPO baseline across multiple backbones and benchmarks.
  arXiv  Detail & Related papers  (2026-05-11T17:59:25Z)
• Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment [43.692750193227674]
  Adversarial training is effective on balanced datasets, but its robustness degrades under longtailed class distributions.<n>We propose Manifold-Constrained Adversarial Training (MCAT), a unified framework that enforces the semantic validity of adversarial examples.
  arXiv  Detail & Related papers  (2026-05-04T03:25:53Z)
• Taming the Judge: Deconflicting AI Feedback for Stable Reinforcement Learning [46.661195064495]
  This work introduces an end to end framework to detect and resolve inconsistencies within the reinforcement learning training loop.<n>Our framework features two core contributions: the Conflict Detection Rate (CDR), a novel metric to quantify judgment conflicts, and Deconflicted Graph Rewards (DGR), a signal-purification framework.<n>Experiments confirm that our framework significantly improves training stability and model performance over strong baselines.
  arXiv  Detail & Related papers  (2025-10-17T10:34:59Z)
• Gradient Reweighting: Towards Imbalanced Class-Incremental Learning [8.438092346233054]
  Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data. A major challenge of CIL arises when applying to real-world data characterized by non-uniform distribution. We show that this dual imbalance issue causes skewed gradient updates with biased weights in FC layers, thus inducing over/under-fitting and catastrophic forgetting in CIL.
  arXiv  Detail & Related papers  (2024-02-28T18:08:03Z)
• Long-Tail Learning with Rebalanced Contrastive Loss [1.4443576276330394]
  We present Rebalanced Contrastive Learning (RCL), an efficient means to increase the long tail classification accuracy. RCL addresses three main aspects: Feature space balancedness, Intra-Class compactness and Regularization. Our experiments on three benchmark datasets demonstrate the richness of the learnt embeddings and increased top-1 balanced accuracy RCL provides to the BCL framework.
  arXiv  Detail & Related papers  (2023-12-04T09:27:03Z)
• Long-Tailed Learning as Multi-Objective Optimization [29.012779934262973]
  We argue that the seesaw dilemma is derived from gradient imbalance of different classes. We propose a Gradient-Balancing Grouping (GBG) strategy to gather the classes with similar gradient directions.
  arXiv  Detail & Related papers  (2023-10-31T14:30:31Z)
• Dual Compensation Residual Networks for Class Imbalanced Learning [98.35401757647749]
  We propose Dual Compensation Residual Networks to better fit both tail and head classes. An important factor causing overfitting is that there is severe feature drift between training and test data on tail classes. We also propose a Residual Balanced Multi-Proxies classifier to alleviate the under-fitting issue.
  arXiv  Detail & Related papers  (2023-08-25T04:06:30Z)
• Leveraging Angular Information Between Feature and Classifier for Long-tailed Learning: A Prediction Reformulation Approach [90.77858044524544]
  We reformulate the recognition probabilities through included angles without re-balancing the classifier weights. Inspired by the performance improvement of the predictive form reformulation, we explore the different properties of this angular prediction. Our method is able to obtain the best performance among peer methods without pretraining on CIFAR10/100-LT and ImageNet-LT.
  arXiv  Detail & Related papers  (2022-12-03T07:52:48Z)
• Relieving Long-tailed Instance Segmentation via Pairwise Class Balance [85.53585498649252]
  Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. We propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences.
  arXiv  Detail & Related papers  (2022-01-08T07:48:36Z)
• You Only Need End-to-End Training for Long-Tailed Recognition [8.789819609485225]
  Cross-entropy loss tends to produce highly correlated features on imbalanced data. We propose two novel modules, Block-based Relatively Balanced Batch Sampler (B3RS) and Batch Embedded Training (BET) Experimental results on the long-tailed classification benchmarks, CIFAR-LT and ImageNet-LT, demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2021-12-11T11:44:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.