Making Reconstruction FID Predictive of Diffusion Generation FID

• URL: http://arxiv.org/abs/2603.05630v1
• Date: Thu, 05 Mar 2026 19:39:01 GMT
• Title: Making Reconstruction FID Predictive of Diffusion Generation FID
• Abstract summary: Reconstruction FID (rFID) of a VAE is poorly correlated with the generation FID (gFID) of a latent diffusion model.<n>We propose interpolated FID (iFID), a simple variant of rFID that exhibits a strong correlation with gFID.<n>iFID is the first metric to demonstrate a strong correlation with diffusion gFID, achieving Pearson linear and Spearman rank correlations approximately 0.85.
• Score: 31.649203442859882
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: It is well known that the reconstruction FID (rFID) of a VAE is poorly correlated with the generation FID (gFID) of a latent diffusion model. We propose interpolated FID (iFID), a simple variant of rFID that exhibits a strong correlation with gFID. Specifically, for each element in the dataset, we retrieve its nearest neighbor (NN) in the latent space and interpolate their latent representations. We then decode the interpolated latent and compute the FID between the decoded samples and the original dataset. Additionally, we refine the claim that rFID correlates poorly with gFID, by showing that rFID correlates with sample quality in the diffusion refinement phase, whereas iFID correlates with sample quality in the diffusion navigation phase. Furthermore, we provide an explanation for why iFID correlates well with gFID, and why reconstruction metrics are negatively correlated with gFID, by connecting to results in the diffusion generalization and hallucination. Empirically, iFID is the first metric to demonstrate a strong correlation with diffusion gFID, achieving Pearson linear and Spearman rank correlations approximately 0.85. The source code is provided in https://github.com/tongdaxu/Making-rFID-Predictive-of-Diffusion-gFID.

Related papers

• The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation [55.62875959637507]
  We treat FID as a random variable on a two-axis panel of training and generation seeds.<n>We measure its variance directly on several hundred SiT networks trained on class-conditional ImageNet 256x256.
  arXiv  Detail & Related papers  (2026-06-18T17:49:32Z)
• Triple Spectral Fusion for Sensor-based Human Activity Recognition [86.21994396715074]
  This paper proposes a novel triple spectral fusion framework tailored for sensor-based human activity recognition (HAR)<n>We develop an adaptive complementary filtering technique for noise suppression and organize each IMU's sensors into posture and motion modality nodes.<n>An adaptive wavelet frequency selection approach is implemented to suppress context redundancy and shorten the length of features.
  arXiv  Detail & Related papers  (2026-05-04T15:42:58Z)
• Generative MIMO Beam Map Construction for Location Recovery and Beam Tracking [67.65578956523403]
  This paper proposes a generative framework to recover location labels directly from sparse channel state information (CSI) measurements.<n>Instead of directly storing raw CSI, we learn a compact low-dimensional radio map embedding and leverage a generative model to reconstruct the high-dimensional CSI.<n> Numerical experiments demonstrate that the proposed model can improve localization accuracy by over 30% and achieve a 20% capacity gain in non-line-of-sight (NLOS) scenarios.
  arXiv  Detail & Related papers  (2025-11-21T07:25:49Z)
• Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning [81.98675881423131]
  This research addresses the challenge of developing a universal deepfake detector that can effectively identify unseen deepfake images. Existing frequency-based paradigms have relied on frequency-level artifacts introduced during the up-sampling in GAN pipelines to detect forgeries. We introduce a novel frequency-aware approach called FreqNet, centered around frequency domain learning, specifically designed to enhance the generalizability of deepfake detectors.
  arXiv  Detail & Related papers  (2024-03-12T01:28:00Z)
• A Novel RFID Authentication Protocol Based on A Block-Order-Modulus Variable Matrix Encryption Algorithm [33.418596635960085]
  authentication for mobile radio frequency identification (RFID) systems with low-cost RFID sensor tags is studied. Numerical results demonstrate that the proposed AM-SUEO-DBLTKM algorithm can save 99.59% of tag storage over traditional algorithms.
  arXiv  Detail & Related papers  (2023-12-17T02:55:13Z)
• RFID-Assisted Indoor Localization Using Hybrid Wireless Data Fusion [0.5753274939310764]
  Wireless localization is essential for tracking objects in indoor environments. Internet of Things (IoT) enables localization through its diverse wireless communication protocols. In this paper, a hybrid section-based indoor localization method using a developed Radio Frequency Identification (RFID) tracking device and multiple IoT wireless technologies is proposed.
  arXiv  Detail & Related papers  (2023-07-28T12:02:27Z)
• Persistent Animal Identification Leveraging Non-Visual Markers [71.14999745312626]
  We aim to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time. This is a very challenging problem due to (i) the lack of distinguishing visual features for each mouse, and (ii) the close confines of the scene with constant occlusion. Our approach achieves 77% accuracy on this animal identification problem, and is able to reject spurious detections when the animals are hidden.
  arXiv  Detail & Related papers  (2021-12-13T17:11:32Z)
• The Tags Are Alright: Robust Large-Scale RFID Clone Detection Through Federated Data-Augmented Radio Fingerprinting [11.03108444237374]
  We propose a novel training framework based on federated machine learning (FML) and data augmentation (DAG) to boost the accuracy of RFID clone detection. To the best of our knowledge, this is the first paper experimentally demonstrating the efficacy of FML and DA on a large device population.
  arXiv  Detail & Related papers  (2021-05-08T10:48:02Z)
• Backpropagating through Fr\'echet Inception Distance [79.81807680370677]
  FastFID can efficiently train generative models with FID as a loss function. Using FID as an additional loss for Generative Adversarial Networks improves their FID.
  arXiv  Detail & Related papers  (2020-09-29T15:04:40Z)
• Monitoring Browsing Behavior of Customers in Retail Stores via RFID Imaging [24.007822566345943]
  We propose TagSee, a multi-person imaging system based on monostatic RFID imaging. We implement TagSee using a Impinj Speedway R420 reader and SMARTRAC DogBone RFID tags. TagSee can achieve a TPR of more than 90% and a FPR of less than 10% in multi-person scenarios using training data from just 3-4 users.
  arXiv  Detail & Related papers  (2020-07-07T16:36:24Z)
• A Compressive Sensing Approach for Federated Learning over Massive MIMO Communication Systems [82.2513703281725]
  Federated learning is a privacy-preserving approach to train a global model at a central server by collaborating with wireless devices. We present a compressive sensing approach for federated learning over massive multiple-input multiple-output communication systems.
  arXiv  Detail & Related papers  (2020-03-18T05:56:27Z)

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.