Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache

• URL: http://arxiv.org/abs/2511.18811v1
• Date: Mon, 24 Nov 2025 06:30:08 GMT
• Title: Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache
• Abstract summary: Human-Object Interaction (HOI) detection is a fundamental task in computer vision, empowering machines to comprehend human-object relationships in diverse real-world scenarios.<n>Recent advances in VLMs have significantly improved HOI detection by leveraging rich cross-modal representations.<n>Most existing VLM-based approaches rely heavily on additional training or prompt tuning, resulting in substantial computational overhead and limited scalability.<n>We propose the Adaptive Diversity Cache (ADC) module, a novel training-free and plug-and-play mechanism designed to mitigate long-tail bias in HOI detection.
• Score: 16.846940736164537
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Human-Object Interaction (HOI) detection is a fundamental task in computer vision, empowering machines to comprehend human-object relationships in diverse real-world scenarios. Recent advances in VLMs have significantly improved HOI detection by leveraging rich cross-modal representations. However, most existing VLM-based approaches rely heavily on additional training or prompt tuning, resulting in substantial computational overhead and limited scalability, particularly in long-tailed scenarios where rare interactions are severely underrepresented. In this paper, we propose the Adaptive Diversity Cache (ADC) module, a novel training-free and plug-and-play mechanism designed to mitigate long-tail bias in HOI detection. ADC constructs class-specific caches that accumulate high-confidence and diverse feature representations during inference. The method incorporates frequency-aware cache adaptation that favors rare categories and is designed to enable robust prediction calibration without requiring additional training or fine-tuning. Extensive experiments on HICO-DET and V-COCO datasets show that ADC consistently improves existing HOI detectors, achieving up to +8.57\% mAP gain on rare categories and +4.39\% on the full dataset, demonstrating its effectiveness in mitigating long-tail bias while preserving overall performance.

Related papers

• FAIM: Frequency-Aware Interactive Mamba for Time Series Classification [87.84511960413715]
  Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition.<n>We propose FAIM, a lightweight Frequency-Aware Interactive Mamba model.<n>We show that FAIM consistently outperforms existing state-of-the-art (SOTA) methods, achieving a superior trade-off between accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-11-26T08:36:33Z)
• Adaptive Cache Enhancement for Test-Time Adaptation of Vision-Language Models [6.403304540670581]
  Vision-language models (VLMs) exhibit remarkable zero-shot generalization but suffer performance degradation under distribution shifts.<n>Test-Time Adaptation (TTA) addresses this challenge by enabling online optimization of VLMs during inference, eliminating the need for annotated data.<n>We introduce the Adaptive Cache Enhancement (ACE) framework, which constructs a robust cache by selectively storing high-confidence or low-entropy image embeddings per class.
  arXiv  Detail & Related papers  (2025-08-11T03:03:34Z)
• Real-Time Decorrelation-Based Anomaly Detection for Multivariate Time Series [1.4472678336151885]
  Anomaly detection plays a vital role across a wide range of real-world domains.<n>Demand for real-time AD has surged with the rise of the (Industrial) Internet of Things.<n>We propose DAD, a novel real-time decorrelation-based anomaly detection method.
  arXiv  Detail & Related papers  (2025-07-10T08:56:40Z)
• USAD: End-to-End Human Activity Recognition via Diffusion Model with Spatiotemporal Attention [8.061018589897277]
  Human activity recognition is a task that finds broad applications in health monitoring, safety protection, and sports analysis.<n>Despite proliferating research, human activity recognition still faces key challenges, including the scarcity of labeled samples for rare activities.<n>This paper proposes a comprehensive optimization approach centered on multi-attention interaction mechanisms.
  arXiv  Detail & Related papers  (2025-07-03T17:38:44Z)
• Towards Efficient and General-Purpose Few-Shot Misclassification Detection for Vision-Language Models [25.51735861729728]
  Modern neural networks often exhibit overconfidence for misclassified predictions, highlighting the need for confidence estimation to detect errors.<n>We exploit vision language model (VLM) leveraging text information to establish an efficient and general-purpose misclassification detection framework.<n>By harnessing the power of VLM, we construct FSMisD, a Few-Shot prompt learning framework for MisD to refrain from training from scratch and therefore improve tuning efficiency.
  arXiv  Detail & Related papers  (2025-03-26T12:31:04Z)
• UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning [35.62208317531141]
  We advocate and introduce the unrolling paradigm, also referred to as "learning to optimize"<n>Our unrolling approach covers various statistical feature distributions and pre-training paradigms.<n>We report comprehensive experiments, which cover a breadth of fine-grained downstream image classification tasks.
  arXiv  Detail & Related papers  (2024-12-21T19:01:57Z)
• CAVE-Net: Classifying Abnormalities in Video Capsule Endoscopy [0.1937002985471497]
  We propose an ensemble-based approach to improve diagnostic accuracy in analyzing complex image datasets.<n>We leverage the unique feature extraction capabilities of each model to enhance the overall accuracy.<n>By using these methods, the proposed framework, CAVE-Net, provides robust feature discrimination and improved classification results.
  arXiv  Detail & Related papers  (2024-10-26T17:25:08Z)
• Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark [101.23684938489413]
  Anomaly detection (AD) is often focused on detecting anomalies for industrial quality inspection and medical lesion examination. This work first constructs a large-scale and general-purpose COCO-AD dataset by extending COCO to the AD field. Inspired by the metrics in the segmentation field, we propose several more practical threshold-dependent AD-specific metrics.
  arXiv  Detail & Related papers  (2024-04-16T17:38:26Z)
• Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory [64.11870454160614]
  We propose an efficient Adaptive HOI Detector with Concept-guided Memory (ADA-CM) ADA-CM has two operating modes. The first mode makes it tunable without learning new parameters in a training-free paradigm. Our proposed method achieves competitive results with state-of-the-art on the HICO-DET and V-COCO datasets with much less training time.
  arXiv  Detail & Related papers  (2023-09-07T13:10:06Z)
• Explaining Cross-Domain Recognition with Interpretable Deep Classifier [100.63114424262234]
  Interpretable Deep (IDC) learns the nearest source samples of a target sample as evidence upon which the classifier makes the decision. Our IDC leads to a more explainable model with almost no accuracy degradation and effectively calibrates classification for optimum reject options.
  arXiv  Detail & Related papers  (2022-11-15T15:58:56Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
  In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
  arXiv  Detail & Related papers  (2020-03-10T03:10:41Z)
• Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis [76.46004354572956]
  We introduce an unsupervised domain adaptation approach for person re-identification. Experimental results show that the proposed ktCUDA and SHRED approach achieves an average improvement of +5.7 mAP in re-identification performance.
  arXiv  Detail & Related papers  (2020-01-14T17:43:52Z)

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.