VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition

• URL: http://arxiv.org/abs/2609.04948v1
• Date: Fri, 04 Sep 2026 09:55:12 GMT
• Title: VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition
• Abstract summary: VICAL is a framework that improves long-tailed recognition not by enforcing expert diversity, but by reducing prediction variance.<n>Our approach comprises two key components: Self-Consistency Learning and Deep Ensemble Distillation.<n>Our experiments on CIFAR-LT, ImageNet-LT, and iist 2018 show that VICAL consistently outperforms state-of-the-art methods.
• Score: 32.48884030865545
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-expert models have become the dominant paradigm for long-tailed learning, largely attributed to their presumed ability to benefit from expert diversity. However, we revisit this central assumption and reveal that diversity induced by logit adjustment or explicit regularizers does not guarantee better ensemble accuracy. Our work suggests that multi-expert models benefit more from variance reduction than diversity maximization. We introduce \textbf{VICAL}, a \textbf{VI}cinal \textbf{C}onsistency \textbf{AL}ignment framework that improves long-tailed recognition not by enforcing expert diversity, but by reducing prediction variance. Specifically, our approach comprises two key components: Self-Consistency Learning and Deep Ensemble Distillation. Self-Consistency Learning discourages reliance on unstable high-frequency information, smoothing the local loss landscape and mitigating overfitting, especially for tail classes. Deep Ensemble Distillation promotes cross-expert low-frequency semantic agreement using a low-resolution view, thereby sidestepping optimization conflicts with established knowledge. Extensive experiments on CIFAR-LT, ImageNet-LT, and iNaturalist 2018 show that VICAL consistently outperforms state-of-the-art methods, validating the effectiveness of our consistency-driven design. Our code is available at \href{https://github.com/FlamieZhu/Vicinal-Consistency-Alignment}{VICAL}.

Related papers

• Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning [4.9788177236136635]
  Federated Learning (FL) emerged as a promising distributed machine learning paradigm.<n> extending FL to the class incremental learning scenarios introduces unique challenges.<n>We propose textbfFisher-Routed textbfMitextbfXture of Experts for textbfFederated Class-Incremental Learning (textscFedFMX)
  arXiv  Detail & Related papers  (2026-06-27T09:45:52Z)
• TRACER: Persistent Regularization for Robust Multimodal Finetuning [15.846967169292789]
  We develop a theoretical framework for multimodal contrastive finetuning, yielding closed-form solutions and a geometric decomposition for each strategy.<n>We prove that a weighted moving average teacher maintains a persistent regularizing force over finite horizons and yields bias-free convergence in the task subspace.<n>Experiments on CLIP finetuning demonstrate consistent OOD accuracy and calibration gains across three backbone architectures.
  arXiv  Detail & Related papers  (2026-05-28T05:34:23Z)
• Dual-Expert Consistency Model for Efficient and High-Quality Video Generation [57.33788820909211]
  We propose a parameter-efficient textbfDual-Expert Consistency Model(DCM), where a semantic expert focuses on learning semantic layout and motion, while a detail expert specializes in fine detail refinement.<n>Our approach achieves state-of-the-art visual quality with significantly reduced sampling steps, demonstrating the effectiveness of expert specialization in video diffusion model distillation.
  arXiv  Detail & Related papers  (2025-06-03T17:55:04Z)
• A Unified Virtual Mixture-of-Experts Framework:Enhanced Inference and Hallucination Mitigation in Single-Model System [9.764336669208394]
  Generative models, such as GPT and BERT, have significantly improved performance in tasks like text generation and summarization.<n>However, hallucinations "where models generate non-factual or misleading content" are especially problematic in smaller-scale architectures.<n>We propose a unified Virtual Mixture-of-Experts (MoE) fusion strategy that enhances inference performance and mitigates hallucinations in a single Qwen 1.5 0.5B model.
  arXiv  Detail & Related papers  (2025-04-01T11:38:01Z)
• MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition [14.998014782981663]
  We propose More Diverse experts with Consistency Self-distillation (MDCS) to bridge the gap left by earlier methods. Our MDCS approach consists of two core components: Diversity Loss (DL) and Consistency Self-distillation (CS)
  arXiv  Detail & Related papers  (2023-08-19T06:21:22Z)
• A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning [63.20009081099896]
  We provide a unifying framework for the design and analysis of multicalibrated predictors. We exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multicalibration learning problems.
  arXiv  Detail & Related papers  (2023-02-21T18:24:17Z)
• Trusted Multi-View Classification with Dynamic Evidential Fusion [73.35990456162745]
  We propose a novel multi-view classification algorithm, termed trusted multi-view classification (TMC) TMC provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. Both theoretical and experimental results validate the effectiveness of the proposed model in accuracy, robustness and trustworthiness.
  arXiv  Detail & Related papers  (2022-04-25T03:48:49Z)
• Revisiting Consistency Regularization for Semi-Supervised Learning [80.28461584135967]
  We propose an improved consistency regularization framework by a simple yet effective technique, FeatDistLoss. Experimental results show that our model defines a new state of the art for various datasets and settings.
  arXiv  Detail & Related papers  (2021-12-10T20:46:13Z)
• Holistic Deep Learning [3.718942345103135]
  This paper presents a novel holistic deep learning framework that addresses the challenges of vulnerability to input perturbations, overparametrization, and performance instability. The proposed framework holistically improves accuracy, robustness, sparsity, and stability over standard deep learning models.
  arXiv  Detail & Related papers  (2021-10-29T14:46:32Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• Trusted Multi-View Classification [76.73585034192894]
  We propose a novel multi-view classification method, termed trusted multi-view classification. It provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level. The proposed algorithm jointly utilizes multiple views to promote both classification reliability and robustness.
  arXiv  Detail & Related papers  (2021-02-03T13:30:26Z)

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.