Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognition

• URL: http://arxiv.org/abs/2604.27759v1
• Date: Thu, 30 Apr 2026 11:47:33 GMT
• Title: Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognition
• Abstract summary: We propose a differentiable knowledge unit (DKU) that enables modulating the classifier logits.<n>The DKU uses implication rules to represent relationships between task classes and implicit concepts learned entirely from the main task supervision.<n>We evaluate our methods on the PASCAL-VOC, COCO, and MedMNIST datasets.
• Score: 1.151255267176226
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Integrating domain knowledge into deep neural networks is a promising way to improve generalization. Existing methods either encode prior knowledge in the loss function or apply post-processing modules, but both depend on identifying useful symbolic knowledge to integrate. Since such rules are often unavailable in real-world vision tasks, we propose a method for targeted knowledge discovery. We propose a Differentiable Knowledge Unit (DKU) that enables modulating the classifier logits, yielding refined class probabilities. The DKU uses implication rules to represent relationships between task classes and implicit concepts learned entirely from the main task supervision, without requiring concept labels. Concepts are identified by dedicated classifiers, whose probabilities are passed to DKU alongside the primary class probabilities. DKU computes a logic-based adjustment vector via fuzzy inference, which modulates the primary class logits to yield refined class probabilities. When concept classifiers represent concepts that do not support the logical rule structure, the resulting adjustments to the class probabilities do not directly minimize the supervision loss. Consequently, optimizing the supervision loss on these adjusted class probabilities implicitly trains the concept classifiers. We construct the rule base so that bidirectional logical relations connect concepts and classes. We enforce the concepts to be distinct from each other and with respect to the classes. This design enforces a clean supervision signal for concept learning. We evaluate our methods on the PASCAL-VOC, COCO, and MedMNIST datasets. We demonstrate improvement through our knowledge integration across these datasets. We conduct domain generalization and hard-sample ablation studies and find that our implicit knowledge discovery and integration outperforms the baseline.

Related papers

• CLARK: Closed-loop Learning for Adaptive Reasoning over Knowledge Graphs [2.2889981393105554]
  CLARK (Closed-loop Learning for Adaptive Reasoning over Knowledge Graphs) is a framework that integrates knowledge graphs, symbolic rule mining, and probabilistic reasoning.<n>We evaluate CLARK on two medical datasets, analysing both rule quality and downstream classification performance.
  arXiv  Detail & Related papers  (2026-07-22T10:30:45Z)
• Incomplete Multi-View Multi-Label Classification via Shared Codebook and Fused-Teacher Self-Distillation [39.27376279295644]
  We introduce a more structured mechanism for consistent representation learning.<n>We learn discrete consistent representations through a multi-view shared codebook and cross-view reconstruction.<n>In addition, we introduce a fused-teacher self-distillation framework.
  arXiv  Detail & Related papers  (2026-04-05T16:22:38Z)
• MeGU: Machine-Guided Unlearning with Target Feature Disentanglement [73.49657372882082]
  We propose a novel framework that guides unlearning through concept-aware re-alignment.<n>MeGU enables controlled and selective forgetting, effectively mitigating both under-unlearning and over-unlearning.
  arXiv  Detail & Related papers  (2026-02-19T05:20:31Z)
• AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis [38.16978432272716]
  The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions. While CLIP provides both explainability and zero-shot classification capability, its pre-training on generic image and text data may limit its classification accuracy and applicability to medical image diagnostic tasks. This paper takes an unconventional approach by re-examining the CBM framework through the lens of its geometrical representation as a simple linear classification system.
  arXiv  Detail & Related papers  (2024-08-04T11:59:09Z)
• Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models [79.28821338925947]
  Domain-Class Incremental Learning is a realistic but challenging continual learning scenario. To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability. This incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability. Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy overhead. We propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of
  arXiv  Detail & Related papers  (2024-07-07T12:19:37Z)
• Set-to-Sequence Ranking-based Concept-aware Learning Path Recommendation [49.85548436111153]
  We propose a novel framework named Set-to-Sequence Ranking-based Concept-aware Learning Path Recommendation (SRC) SRC formulates the recommendation task under a set-to-sequence paradigm. We conduct extensive experiments on two real-world public datasets and one industrial dataset.
  arXiv  Detail & Related papers  (2023-06-07T08:24:44Z)
• Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace [1.6574413179773757]
  Concept-Centric Transformers is a simple yet effective configuration of the shared global workspace for interpretability. We show that our model achieves better classification accuracy than all baselines across all problems.
  arXiv  Detail & Related papers  (2023-05-25T06:37:39Z)
• Hierarchically Structured Task-Agnostic Continual Learning [0.0]
  We take a task-agnostic view of continual learning and develop a hierarchical information-theoretic optimality principle. We propose a neural network layer, called the Mixture-of-Variational-Experts layer, that alleviates forgetting by creating a set of information processing paths. Our approach can operate in a task-agnostic way, i.e., it does not require task-specific knowledge, as is the case with many existing continual learning algorithms.
  arXiv  Detail & Related papers  (2022-11-14T19:53:15Z)
• Prior Knowledge Guided Unsupervised Domain Adaptation [82.9977759320565]
  We propose a Knowledge-guided Unsupervised Domain Adaptation (KUDA) setting where prior knowledge about the target class distribution is available. In particular, we consider two specific types of prior knowledge about the class distribution in the target domain: Unary Bound and Binary Relationship. We propose a rectification module that uses such prior knowledge to refine model generated pseudo labels.
  arXiv  Detail & Related papers  (2022-07-18T18:41:36Z)
• Active Refinement for Multi-Label Learning: A Pseudo-Label Approach [84.52793080276048]
  Multi-label learning (MLL) aims to associate a given instance with its relevant labels from a set of concepts. Previous works of MLL mainly focused on the setting where the concept set is assumed to be fixed. Many real-world applications require introducing new concepts into the set to meet new demands.
  arXiv  Detail & Related papers  (2021-09-29T19:17:05Z)
• Fast Few-Shot Classification by Few-Iteration Meta-Learning [173.32497326674775]
  We introduce a fast optimization-based meta-learning method for few-shot classification. Our strategy enables important aspects of the base learner objective to be learned during meta-training. We perform a comprehensive experimental analysis, demonstrating the speed and effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-10-01T15:59:31Z)

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.