Robustness Evaluation for Video Models with Reinforcement Learning

• URL: http://arxiv.org/abs/2506.05431v1
• Date: Thu, 05 Jun 2025 08:38:09 GMT
• Title: Robustness Evaluation for Video Models with Reinforcement Learning
• Authors: Ashwin Ramesh Babu, Sajad Mousavi, Vineet Gundecha, Sahand Ghorbanpour, Avisek Naug, Antonio Guillen, Ricardo Luna Gutierrez, Soumyendu Sarkar,
• Abstract summary: We propose a multi-agent reinforcement learning approach that learns cooperatively to identify the given video's sensitive spatial and temporal regions.<n>Our method outperforms the state-of-the-art solutions on the Lp metric and the average queries.
• Score: 4.0196072781228285
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evaluating the robustness of Video classification models is very challenging, specifically when compared to image-based models. With their increased temporal dimension, there is a significant increase in complexity and computational cost. One of the key challenges is to keep the perturbations to a minimum to induce misclassification. In this work, we propose a multi-agent reinforcement learning approach (spatial and temporal) that cooperatively learns to identify the given video's sensitive spatial and temporal regions. The agents consider temporal coherence in generating fine perturbations, leading to a more effective and visually imperceptible attack. Our method outperforms the state-of-the-art solutions on the Lp metric and the average queries. Our method enables custom distortion types, making the robustness evaluation more relevant to the use case. We extensively evaluate 4 popular models for video action recognition on two popular datasets, HMDB-51 and UCF-101.

Related papers

• Admitting Ignorance Helps the Video Question Answering Models to Answer [82.22149677979189]
  We argue that models often establish shortcuts, resulting in spurious correlations between questions and answers.<n>We propose a novel training framework in which the model is compelled to acknowledge its ignorance when presented with an intervened question.<n>In practice, we integrate a state-of-the-art model into our framework to validate its effectiveness.
  arXiv  Detail & Related papers  (2025-01-15T12:44:52Z)
• Patch Spatio-Temporal Relation Prediction for Video Anomaly Detection [19.643936110623653]
  Video Anomaly Detection (VAD) aims to identify abnormalities within a specific context and timeframe. Recent deep learning-based VAD models have shown promising results by generating high-resolution frames. We propose a self-supervised learning approach for VAD through an inter-patch relationship prediction task.
  arXiv  Detail & Related papers  (2024-03-28T03:07:16Z)
• Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models [16.36416048893487]
  We introduce the Breaking Temporal Consistency (BTC) method, which is the first attempt to incorporate temporal information into video attacks using image models. Our approach is simple but effective at attacking unseen video models. Our approach surpasses existing methods in terms of effectiveness on various datasets.
  arXiv  Detail & Related papers  (2023-11-17T07:39:42Z)
• A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selection [14.089888316857426]
  This paper focuses on weakly supervised video anomaly detection. We develop a lightweight video anomaly detection model. We show that our model can achieve comparable or even superior AUC score compared to the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-09T01:23:08Z)
• Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration [59.6021678234829]
  We propose a novel method to restore the intermediate features for two sparsely sampled and adjacent video frames. With the integration of our method, the efficiency of three commonly used baselines has been improved by over 50%, with a mere 0.5% reduction in recognition accuracy.
  arXiv  Detail & Related papers  (2023-07-27T13:52:42Z)
• Leaping Into Memories: Space-Time Deep Feature Synthesis [93.10032043225362]
  We propose LEAPS, an architecture-independent method for synthesizing videos from internal models. We quantitatively and qualitatively evaluate the applicability of LEAPS by inverting a range of architectures convolutional attention-based on Kinetics-400.
  arXiv  Detail & Related papers  (2023-03-17T12:55:22Z)
• Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos [0.0]
  We design the novel Adversarial spatial-temporal Focus (AstFocus) attack on videos, which performs attacks on the simultaneously focused key frames and key regions. By continuously querying, the reduced searching space composed of key frames and key regions is becoming precise. Experiments on four mainstream video recognition models and three widely used action recognition datasets demonstrate that the proposed AstFocus attack outperforms the SOTA methods.
  arXiv  Detail & Related papers  (2023-01-03T00:28:57Z)
• CONVIQT: Contrastive Video Quality Estimator [63.749184706461826]
  Perceptual video quality assessment (VQA) is an integral component of many streaming and video sharing platforms. Here we consider the problem of learning perceptually relevant video quality representations in a self-supervised manner. Our results indicate that compelling representations with perceptual bearing can be obtained using self-supervised learning.
  arXiv  Detail & Related papers  (2022-06-29T15:22:01Z)
• Video Salient Object Detection via Contrastive Features and Attention Modules [106.33219760012048]
  We propose a network with attention modules to learn contrastive features for video salient object detection. A co-attention formulation is utilized to combine the low-level and high-level features. We show that the proposed method requires less computation, and performs favorably against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-11-03T17:40:32Z)
• Efficient Modelling Across Time of Human Actions and Interactions [92.39082696657874]
  We argue that current fixed-sized-temporal kernels in 3 convolutional neural networks (CNNDs) can be improved to better deal with temporal variations in the input. We study how we can better handle between classes of actions, by enhancing their feature differences over different layers of the architecture. The proposed approaches are evaluated on several benchmark action recognition datasets and show competitive results.
  arXiv  Detail & Related papers  (2021-10-05T15:39:11Z)

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.