MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration

• URL: http://arxiv.org/abs/2607.10985v1
• Date: Mon, 13 Jul 2026 01:18:32 GMT
• Title: MED-DSLC: Multi-Expert-Domain Classification via Domain Supervision and Logit Calibration
• Abstract summary: Vision-language models (VLMs) enable zero-shot classification by comparing image features with text prompts in a shared embedding space.<n>VLMs are often adapted to fine-grained domains using techniques such as LoRA.<n>This leads to a highly fragmented model ecosystem, with thousands of specialized models.
• Score: 42.68764270775848
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models (VLMs) such as CLIP enable zero-shot classification by comparing image features with text prompts in a shared embedding space. A fundamental property underlying this capability is the global comparability of logits across arbitrary candidate classes. However, VLMs are often adapted to fine-grained domains using techniques such as LoRA. While this improves in-domain accuracy, out-of-domain accuracy degrades. This leads to a highly fragmented model ecosystem, with thousands of specialized models. Multi-Expert-Domain classification seeks to address this problem, by merging LoRAs trained independently on specialized domains. However, due to the independent training, the various domain experts no longer produce globally calibrated logits. As a result, when evaluating over the union of multiple domain-specific class sets, heterogeneous logit scales induce cross-domain interference and artificially high confidence for out-of-domain classes, inducing prediction errors. In this work, we identify domain supervision and cross-domain logit miscalibration as the key issue to scalable multi-domain zero-shot recognition. We propose MED-DSLC, combining domain supervised training and domain-wise logit scaling, to explicitly restore global logit comparability. MED-DSLC is a lightweight solution for MED classification, which is shown to preserve within-domain discrimination while reducing cross-domain logit interference with minimal data. Extensive experiments across diverse fine-grained benchmarks demonstrate that it substantially improves mean accuracy (+15\%), cross-domain robustness, and scalability in the size of MED classification problem. Our results show that restoring output-level calibration is essential under highly data imbalanced settings for achieving a truly zero-shot VLM under multi-domain specialization.

Related papers

• Domain-Skewed Federated Learning with Feature Decoupling and Calibration [35.05951359908686]
  Federated learning (FL) allows distributed clients to collaboratively train a global model in a privacy-preserving manner.<n>One major challenge is domain skew, where clients' data originating from diverse domains may hinder the aggregated global model from learning a consistent representation space.<n>We propose Federated Feature Decoupling andrimi ($F2$DC), which liberates valuable class-relevant information by calibrating the domain-specific biased features.
  arXiv  Detail & Related papers  (2026-03-15T06:20:22Z)
• Domain-invariant Mixed-domain Semi-supervised Medical Image Segmentation with Clustered Maximum Mean Discrepancy Alignment [11.298724831730675]
  We propose a domain-invariant mixed-domain semi-supervised segmentation framework.<n>A Copy-Paste Mechanism (CPM) augments the training set by transferring informative regions across domains.<n>A Cluster Maximum Mean Discrepancy (CMMD) block clusters unlabeled features and aligns them with labeled anchors.
  arXiv  Detail & Related papers  (2026-01-23T18:23:03Z)
• Domain Generalization via Selective Consistency Regularization for Time Series Classification [16.338176636365752]
  Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains. We propose a novel representation learning methodology that selectively enforces prediction consistency between source domains.
  arXiv  Detail & Related papers  (2022-06-16T01:57:35Z)
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation [108.63914324182984]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. We build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets.
  arXiv  Detail & Related papers  (2021-06-10T06:32:30Z)
• AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection [90.18752912204778]
  Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training. Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
  arXiv  Detail & Related papers  (2021-06-10T05:01:20Z)
• Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation [74.71931918541748]
  We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA. We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process. We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-03T01:33:14Z)
• Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation [74.3349233035632]
  Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) do not consider an inter-class variation within the target domain itself or estimated category. We introduce a learnable clustering module, and a novel domain adaptation framework called cross-domain grouping and alignment. Our method consistently boosts the adaptation performance in semantic segmentation, outperforming the state-of-the-arts on various domain adaptation settings.
  arXiv  Detail & Related papers  (2020-12-15T11:36:21Z)
• Cross-domain Detection via Graph-induced Prototype Alignment [114.8952035552862]
  We propose a Graph-induced Prototype Alignment (GPA) framework to seek for category-level domain alignment. In addition, in order to alleviate the negative effect of class-imbalance on domain adaptation, we design a Class-reweighted Contrastive Loss. Our approach outperforms existing methods with a remarkable margin.
  arXiv  Detail & Related papers  (2020-03-28T17:46:55Z)

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.