LogitDynamics: Reliable ViT Error Detection from Layerwise Logit Trajectories

• URL: http://arxiv.org/abs/2604.10643v1
• Date: Sun, 12 Apr 2026 13:43:40 GMT
• Title: LogitDynamics: Reliable ViT Error Detection from Layerwise Logit Trajectories
• Abstract summary: We study error prediction in Vision Transformers (ViTs)<n>Motivated by internal-signal hallucination detection in large language models, we investigate whether similar depth-wise signals exist inViTs.<n>By attaching lightweight linear heads to intermediate layers, we extract features from the last L layers that capture both the logits of the predicted class and its top-K competitors.<n>A linear probe trained on these features predicts the error indicator.
• Score: 1.4610038284393168
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Reliable confidence estimation is critical when deploying vision models. We study error prediction: determining whether an image classifier's output is correct using only signals from a single forward pass. Motivated by internal-signal hallucination detection in large language models, we investigate whether similar depth-wise signals exist in Vision Transformers (ViTs). We propose a simple method that models how class evidence evolves across layers. By attaching lightweight linear heads to intermediate layers, we extract features from the last L layers that capture both the logits of the predicted class and its top-K competitors, as well as statistics describing instability of top-ranked classes across depth. A linear probe trained on these features predicts the error indicator. Across datasets, our method improves or matches AUCPR over baselines and shows stronger cross-dataset generalization while requiring minimal additional computation.

Related papers

• Latent Fact-Checking: Detecting Misinformation through Activation Engineering [1.3299946892361476]
  We introduce a misinformation detection framework grounded in activation engineering.<n>Our approach elicits a misinformation direction in the residual stream by contrasting activations from paired truthful and false statements.<n>We evaluate the method across 11 models on three fact-checking benchmarks: AVeriTeC, LIAR, and FACTors.
  arXiv  Detail & Related papers  (2026-08-05T18:00:14Z)
• Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark [32.89408229880636]
  Face presentation attack detection remains challenging under cross-dataset evaluation.<n>Do general-purpose vision foundation models encode PAD-relevant information accessible with minimal task-specific training?<n>We evaluate 24 frozen encoders, including self-supervised vision transformers, vision-language encoders, and supervised CNNs.
  arXiv  Detail & Related papers  (2026-07-29T14:52:25Z)
• Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models [51.099179436350376]
  Multimodal large language models (MLLMs) have been increasingly adopted in forensics for their robust semantic understanding.<n>We propose Deep Visual Residual MLLM (Deep-VRM) to preserve early semantic processing while injecting artifact-specific visual signals as a residual path into an intermediate layer.<n>This enables later layers to jointly model semantic reasoning and signal-level forensic cues, and surprisingly, the model learns to adaptively leverage different levels of forensic signals depending on the input.
  arXiv  Detail & Related papers  (2026-06-14T16:05:45Z)
• From Unfamiliar to Familiar: Detecting Pre-training Data via Gradient Deviations in Large Language Models [24.38939297043815]
  Existing methods mainly focus on the likelihood-based statistical features or signals before and after fine-tuning.<n>We propose GDS, a method that identifies pre-training data by probing Gradient Deviation Scores of target samples.<n>GDS achieves state-of-the-art performance with significantly improved cross-dataset transferability over strong baselines.
  arXiv  Detail & Related papers  (2026-03-05T05:21:51Z)
• Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection [7.0229899259286945]
  We show that exploiting inter-sample relationships can significantly improve OOD detection in long-tailed recognition of vision datasets.<n>Our method outperforms the state-of-the-art approaches by a large margin in terms of FPR and tail-class ID classification accuracy.
  arXiv  Detail & Related papers  (2025-11-20T03:31:37Z)
• ICAS: Detecting Training Data from Autoregressive Image Generative Models [38.1625974271413]
  Training data detection has emerged as a critical task for identifying unauthorized data usage in model training.<n>We conduct the first study applying membership inference to this domain.<n>Our approach exhibits strong robustness and generalization under various data transformations.
  arXiv  Detail & Related papers  (2025-07-07T14:50:42Z)
• Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
  We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-20T01:34:13Z)
• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams [52.77024349608834]
  We classify transient noise signals (i.e.glitches) and gravitational waves in data from the Advanced LIGO detectors. We use models with a supervised learning approach, both trained from scratch using the Gravity Spy dataset. We also explore a self-supervised approach, pre-training models with automatically generated pseudo-labels.
  arXiv  Detail & Related papers  (2023-03-24T11:12:37Z)
• DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows [52.31831255787147]
  We introduce a novel technique, DAAIN, to detect out-of-distribution (OOD) inputs and adversarial attacks (AA) Our approach monitors the inner workings of a neural network and learns a density estimator of the activation distribution. Our model can be trained on a single GPU making it compute efficient and deployable without requiring specialized accelerators.
  arXiv  Detail & Related papers  (2021-05-30T22:07:13Z)
• Predicting What You Already Know Helps: Provable Self-Supervised Learning [60.27658820909876]
  Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data. We show a mechanism exploiting the statistical connections between certain em reconstruction-based pretext tasks that guarantee to learn a good representation. We prove the linear layer yields small approximation error even for complex ground truth function class.
  arXiv  Detail & Related papers  (2020-08-03T17:56:13Z)
• Eigen-CAM: Class Activation Map using Principal Components [1.2691047660244335]
  This paper builds on previous ideas to cope with the increasing demand for interpretable, robust, and transparent models. The proposed Eigen-CAM computes and visualizes the principle components of the learned features/representations from the convolutional layers.
  arXiv  Detail & Related papers  (2020-08-01T17:14:13Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

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.