An Empirical Analysis of Optimization Dynamics and Sparsity Boundaries in Large-Scale Pedestrian Attribute Recognition

• URL: http://arxiv.org/abs/2606.14770v1
• Date: Tue, 09 Jun 2026 04:54:56 GMT
• Title: An Empirical Analysis of Optimization Dynamics and Sparsity Boundaries in Large-Scale Pedestrian Attribute Recognition
• Abstract summary: We present a systematic ablation of Multi-Label Focal Loss hyper parameters on a ResNet-18 backbone.<n>A calibrated configuration (alpha=0.50, gamma=2.0) achieves a Macro F1-score of 62.32%, matching BCE baseline.<n>We identify the Sparsity Wall, a hard boundary where positive sample fractions below 0.1% make global loss reweighting ineffective.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pedestrian Attribute Recognition (PAR) is critical for video surveillance, enabling forensic search and re-identification systems. Extreme class imbalance remains a fundamental obstacle when merging PETA and PA-100K into a 109,000-image composite corpus, where minority attributes have positive sample fractions below 1%. This causes standard BCE optimization to suppress rare traits, a phenomenon we term the majority negative class cheating trap. We present a systematic ablation of Multi-Label Focal Loss hyperparameters (alpha and gamma) on a ResNet-18 backbone. A calibrated configuration (alpha=0.50, gamma=2.0) achieves a Macro F1-score of 62.32%, matching BCE baseline while preserving superior hard-example mining and convergence dynamics. Our approach uses pure loss-function engineering with zero computational overhead for edge deployment. We identify the Sparsity Wall, a hard boundary where positive sample fractions below 0.1% make global loss reweighting ineffective, requiring instance-level intervention.

Related papers

• Automating the Expert Eye: A System-Agnostic Deep Learning Framework for Rare Event Discovery in Imbalanced Force Spectroscopy [0.0]
  We present a system-agnostic, interpretable deep learning framework tailored to overcome extreme class imbalance in automated SMFS triage.<n>We evaluated this framework on the complex mechanical unfolding pathways of the R. champanellensis cellulosome.<n>By implementing an empirically dual-weighted triage system, the pipeline automatically discarded 880 background noise traces.
  arXiv  Detail & Related papers  (2026-06-08T14:24:58Z)
• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction [7.356849324535381]
  This study introduces yvsoucom-iterkit, a deterministic and log-driven automated machine learning framework.<n>Experiments on the Pima Indians Diabetes and Stroke datasets across more than 18,000 pipeline configurations reveal a partially redundant search space.<n>The framework achieves strong and stable performance using ensemble models.
  arXiv  Detail & Related papers  (2026-05-19T16:57:56Z)
• Singularity Avoidance in Inverse Kinematics: A Unified Treatment of Classical and Learning-based Methods [0.0]
  We bridge classical singularity-robust IK with rapidly growing learning-based approaches.<n>A systematic taxonomy classifies methods by retained geometric structure and robustness guarantees.<n>We show that pure learning methods fail even on well-conditioned targets.
  arXiv  Detail & Related papers  (2026-04-15T02:14:01Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• SafeBench-Seq: A Homology-Clustered, CPU-Only Baseline for Protein Hazard Screening with Physicochemical/Composition Features and Cluster-Aware Confidence Intervals [26.81598226089532]
  We introduce SafeBench-Seq, a metadata-only, reproducible benchmark and baseline classifier built entirely from public data.<n>To approximate "never-before-seen" threats, we homology-cluster the combined dataset at =40% identity and perform cluster-level holdouts.<n>We report discrimination (AUROC/AUPRC) and screening-operating points (TPR@1% FPR; FPR@95% TPR) with 95% bootstrap confidence intervals (n=200)<n>We quantify probability quality using Brier score, Expected Error (ECE); 15 bins, and reliability diagrams.
  arXiv  Detail & Related papers  (2025-12-19T12:51:31Z)
• Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations [121.39938773554523]
  The Area Under the ROC Curve (AUC) is a pivotal evaluation metric in real-world scenarios with both class imbalance and decision constraints.<n>We present two simple instance-wise minimax reformulations to close the approximation gap of PAUC optimization.<n>The resulting algorithms enjoy a linear per-iteration computational complexity w.r.t. the sample size and a convergence rate of $O(-2/3)$ for typical one-way and two-way PAUCs.
  arXiv  Detail & Related papers  (2025-12-01T02:52:33Z)
• DRL-Guided Neural Batch Sampling for Semi-Supervised Pixel-Level Anomaly Detection [0.0]
  Anomaly detection in industrial visual inspection is challenging due to the scarcity of defective samples.<n>We propose a semi-supervised deep reinforcement learning framework that integrates a neural batch sampler, an autoencoder, and a predictor.
  arXiv  Detail & Related papers  (2025-11-25T12:53:53Z)
• Rethinking LLM Evaluation: Can We Evaluate LLMs with 200x Less Data? [82.09573568241724]
  EssenceBench is a coarse-to-fine framework utilizing an iterative Genetic Algorithm (GA)<n>Our approach yields superior compression results with lower reconstruction error and markedly higher efficiency.<n>On the HellaSwag benchmark (10K samples), our method preserves the ranking of all models shifting within 5% using 25x fewer samples, and achieves 95% ranking preservation shifting within 5% using only 200x fewer samples.
  arXiv  Detail & Related papers  (2025-10-12T05:38:10Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Learning with Multiclass AUC: Theory and Algorithms [141.63211412386283]
  Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics.
  arXiv  Detail & Related papers  (2021-07-28T05:18:10Z)

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.