ZIP: Scalable Crowd Counting via Zero-Inflated Poisson Modeling

• URL: http://arxiv.org/abs/2506.19955v3
• Date: Thu, 31 Jul 2025 14:46:10 GMT
• Title: ZIP: Scalable Crowd Counting via Zero-Inflated Poisson Modeling
• Abstract summary: We introduce ZIP, a scalable crowd counting framework that models blockwise counts with a Zero-Inflated Poisson likelihood.<n>We provide a generalization analysis showing a tighter risk bound for ZIP than MSE-based losses.<n>Experiments on ShanghaiTech A & B, UCF-QNRF, and NWPU-Crowd demonstrate that ZIP consistently surpasses state-of-the-art methods across all model scales.
• Score: 29.570935239024138
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most crowd counting methods directly regress blockwise density maps using Mean Squared Error (MSE) losses. This practice has two key limitations: (1) it fails to account for the extreme spatial sparsity of annotations - over 95% of 8x8 blocks are empty across standard benchmarks, so supervision signals in informative regions are diluted by the predominant zeros; (2) MSE corresponds to a Gaussian error model that poorly matches discrete, non-negative count data. To address these issues, we introduce ZIP, a scalable crowd counting framework that models blockwise counts with a Zero-Inflated Poisson likelihood: a zero-inflation term learns the probability a block is structurally empty (handling excess zeros), while the Poisson component captures expected counts when people are present (respecting discreteness). We provide a generalization analysis showing a tighter risk bound for ZIP than MSE-based losses and DMCount provided that the training resolution is moderately large. To assess the scalability of ZIP, we instantiate it on backbones spanning over 100x in parameters/compute. Experiments on ShanghaiTech A & B, UCF-QNRF, and NWPU-Crowd demonstrate that ZIP consistently surpasses state-of-the-art methods across all model scales.

Related papers

• Median-of-Means as an Extremal Convex Estimator and a Nonconvex Route to the Trimmed Oracle [11.62669179647184]
  We develop a family block-Lp estimators for robust learning with heavy-tailed and adversarially corrupted data.<n>We show that the block-Lp objectives have a benign landscape, with all local minima remaining close to the truth and no bad basins.
  arXiv  Detail & Related papers  (2026-09-01T15:39:04Z)
• An Omitted Mode Is a Rare Rule: The Sampling-Verification Danger Law in Continuous Code World Models [0.0]
  GPT-5.x repairs an omitted 1D clamp in 105 of 111 mode-containing synthesis draws.<n>On 2D regions no artifact recovers the rule (0/156); eight targeted interventions leave the failure in place, and positive controls locate it.<n>We prove a class of entry rules exactly consistent with every sample yet harmless at play, so identifiability is a measurable property of the instrument.
  arXiv  Detail & Related papers  (2026-08-18T16:09:51Z)
• Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation [55.47411235954028]
  We recast imputation under missing completely at random as density estimation from masked observations.<n>We obtain a convex empirical risk problem with closed form marginals, solvable by a Newton interior point method.<n>The resulting PSD Impute model yields both single and multiple imputations from the same fitted density.
  arXiv  Detail & Related papers  (2026-07-08T15:51:05Z)
• Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection [2.8547732086436306]
  A fundamental limitation of supervised deep learning is "Generalization Collapse"<n>We propose Latent Sculpting, a hierarchical two-stage representation learning framework.<n>We report an 88.89% detection rate on "Infiltration" scenarios.
  arXiv  Detail & Related papers  (2025-12-19T11:37:02Z)
• Perfectly-Private Analog Secure Aggregation in Federated Learning [51.61616734974475]
  In federated learning, multiple parties train models locally and share their parameters with a central server, which aggregates them to update a global model.<n>In this paper, a novel secure parameter aggregation method is proposed that employs the torus rather than a finite field.
  arXiv  Detail & Related papers  (2025-09-10T15:22:40Z)
• Optimal Robust Estimation under Local and Global Corruptions: Stronger Adversary and Smaller Error [10.266928164137635]
  Algorithmic robust statistics has traditionally focused on the contamination model where a small fraction of the samples are arbitrarily corrupted. We consider a recent contamination model that combines two kinds of corruptions: (i) small fraction of arbitrary outliers, as in classical robust statistics, and (ii) local perturbations, where samples may undergo bounded shifts on average. We show that information theoretically optimal error can indeed be achieved in time, under an even emphstronger local perturbation model.
  arXiv  Detail & Related papers  (2024-10-22T17:51:23Z)
• Rejection via Learning Density Ratios [50.91522897152437]
  Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions.<n>We propose a different distributional perspective, where we seek to find an idealized data distribution which maximizes a pretrained model's performance.<n>Our framework is tested empirically over clean and noisy datasets.
  arXiv  Detail & Related papers  (2024-05-29T01:32:17Z)
• CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification [29.570935239024138]
  We propose CLIP-EBC, the first fully CLIP-based model for accurate crowd density estimation.<n>Our EBC framework can improve existing classification-based methods by up to 44.5% on the UCF-QNRF dataset.<n>CLIP-EBC achieves state-of-the-art performance on the NWPU-Crowd test set, with an MAE of 58.2 and an RMSE of 268.5, representing improvements of 8.6% and 13.3% over the previous best method, STEERER.
  arXiv  Detail & Related papers  (2024-03-14T11:08:33Z)
• A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints [87.08677547257733]
  Neuro-symbolic AI bridges the gap between purely symbolic and neural approaches to learning. We show how to maximize the likelihood of a symbolic constraint w.r.t the neural network's output distribution. We also evaluate our approach on Sudoku and shortest-path prediction cast as autoregressive generation.
  arXiv  Detail & Related papers  (2023-12-06T20:58:07Z)
• Resampled Confidence Regions with Exponential Shrinkage for the Regression Function of Binary Classification [0.0]
  We build distribution-free confidence regions for the regression function for any user-chosen confidence level and any finite sample size based on a resampling test.<n>We prove the strong uniform consistency of a new empirical risk based approach for model classes with finite pseudo-dimensions and inverse Lipschitz parameterizations.<n>We also consider a k-nearest neighbors based method, for which we prove strong point boundswise on the probability of exclusion.
  arXiv  Detail & Related papers  (2023-08-03T15:52:27Z)
• Uncertainty Voting Ensemble for Imbalanced Deep Regression [20.176217123752465]
  In this paper, we introduce UVOTE, a method for learning from imbalanced data. We replace traditional regression losses with negative log-likelihood, which also predicts sample-wise aleatoric uncertainty. We show that UVOTE consistently outperforms the prior art, while at the same time producing better-calibrated uncertainty estimates.
  arXiv  Detail & Related papers  (2023-05-24T14:12:21Z)
• $CrowdDiff$: Multi-hypothesis Crowd Density Estimation using Diffusion Models [26.55769846846542]
  Crowd counting is a fundamental problem in crowd analysis which is typically accomplished by estimating a crowd density map and summing over the density values. We present $CrowdDiff$ that generates the crowd density map as a reverse diffusion process. In addition, owing to the nature of the diffusion model, we introduce producing multiple density maps to improve the counting performance.
  arXiv  Detail & Related papers  (2023-03-22T17:58:01Z)
• Compound Batch Normalization for Long-tailed Image Classification [77.42829178064807]
  We propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. The proposed method outperforms existing methods on long-tailed image classification.
  arXiv  Detail & Related papers  (2022-12-02T07:31:39Z)
• Scale-Aware Crowd Counting Using a Joint Likelihood Density Map and Synthetic Fusion Pyramid Network [15.882525477601183]
  We develop a Synthetic Fusion Pyramid Network (SPF-Net) with a scale-aware loss function design for accurate crowd counting. Existing crowd-counting methods assume that the training annotation points were accurate and thus ignore the fact that noisy annotations can lead to large model-learning bias and counting error. This work is the first to properly handle such noise at multiple scales in end-to-end loss design and thus push the crowd counting state-of-the-art.
  arXiv  Detail & Related papers  (2022-11-13T06:52:47Z)
• GP-BART: a novel Bayesian additive regression trees approach using Gaussian processes [1.03590082373586]
  The GP-BART model is an extension of BART which addresses the limitation by assuming GP priors for the predictions of each terminal node among all trees. The model's effectiveness is demonstrated through applications to simulated and real-world data, surpassing the performance of traditional modeling approaches in various scenarios.
  arXiv  Detail & Related papers  (2022-04-05T11:18:44Z)
• Zero-Truncated Poisson Regression for Sparse Multiway Count Data Corrupted by False Zeros [0.0]
  We propose a novel statistical inference methodology for multiway count data that is corrupted by false zeros. Our approach consists of zero-truncating the Poisson distribution to neglect all zero values.
  arXiv  Detail & Related papers  (2022-01-25T00:09:48Z)
• Scaling Structured Inference with Randomization [64.18063627155128]
  We propose a family of dynamic programming (RDP) randomized for scaling structured models to tens of thousands of latent states. Our method is widely applicable to classical DP-based inference. It is also compatible with automatic differentiation so can be integrated with neural networks seamlessly.
  arXiv  Detail & Related papers  (2021-12-07T11:26:41Z)
• Learning to Estimate Without Bias [57.82628598276623]
  Gauss theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance.
  arXiv  Detail & Related papers  (2021-10-24T10:23:51Z)
• Direct Measure Matching for Crowd Counting [59.66286603624411]
  We propose a new measure-based counting approach to regress the predicted density maps to the scattered point-annotated ground truth directly. In this paper, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching.
  arXiv  Detail & Related papers  (2021-07-04T06:37:33Z)
• Distribution Matching for Crowd Counting [51.90971145453012]
  We show that imposing Gaussians to annotations hurts generalization performance. We propose to use Distribution Matching for crowd COUNTing (DM-Count) In terms of Mean Absolute Error, DM-Count outperforms the previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-09-28T04:57:23Z)
• Learning Minimax Estimators via Online Learning [55.92459567732491]
  We consider the problem of designing minimax estimators for estimating parameters of a probability distribution. We construct an algorithm for finding a mixed-case Nash equilibrium.
  arXiv  Detail & Related papers  (2020-06-19T22:49:42Z)
• Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model [50.38446482252857]
  This paper is concerned with the sample efficiency of reinforcement learning, assuming access to a generative model (or simulator) We first consider $gamma$-discounted infinite-horizon Markov decision processes (MDPs) with state space $mathcalS$ and action space $mathcalA$. We prove that a plain model-based planning algorithm suffices to achieve minimax-optimal sample complexity given any target accuracy level.
  arXiv  Detail & Related papers  (2020-05-26T17:53:18Z)

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.