Masking Strategies for Background Bias Removal in Computer Vision Models

• URL: http://arxiv.org/abs/2308.12127v1
• Date: Wed, 23 Aug 2023 13:33:39 GMT
• Title: Masking Strategies for Background Bias Removal in Computer Vision Models
• Abstract summary: This research investigates the impact of background-induced bias on fine-grained image classification. We evaluate standard backbone models such as Conal Neural Network (CNN) and Vision Transformers (ViT) Experiments assess the behavior of CNN and ViT models under different masking strategies.
• Score: 8.168621685852521
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Models for fine-grained image classification tasks, where the difference between some classes can be extremely subtle and the number of samples per class tends to be low, are particularly prone to picking up background-related biases and demand robust methods to handle potential examples with out-of-distribution (OOD) backgrounds. To gain deeper insights into this critical problem, our research investigates the impact of background-induced bias on fine-grained image classification, evaluating standard backbone models such as Convolutional Neural Network (CNN) and Vision Transformers (ViT). We explore two masking strategies to mitigate background-induced bias: Early masking, which removes background information at the (input) image level, and late masking, which selectively masks high-level spatial features corresponding to the background. Extensive experiments assess the behavior of CNN and ViT models under different masking strategies, with a focus on their generalization to OOD backgrounds. The obtained findings demonstrate that both proposed strategies enhance OOD performance compared to the baseline models, with early masking consistently exhibiting the best OOD performance. Notably, a ViT variant employing GAP-Pooled Patch token-based classification combined with early masking achieves the highest OOD robustness.

Related papers

• Segmentation of Bovid Dentition Under Imperfect Annotations: A Comparative Study of Convolutional and Attention Models [3.718942345103135]
  Deep neural networks (DNNs) learn to classify pixels directly.<n>Semantic segmentations crucially depend on expertly designed mask targets.<n>This paper presents a comparative study of segmentation architectures, applied to the B.O.V.I.D. dataset.<n>We evaluate a range of preprocessing and alignment techniques to mitigate the resulting label imperfections.
  arXiv  Detail & Related papers  (2026-08-31T16:29:31Z)
• Directional Gradient Projection for Robust Fine-Tuning of Foundation Models [25.04763038570959]
  Directional Gradient Projection (DiGraP) is a layer-wise trainable method that incorporates directional information from gradients to bridge regularization and multi-objective optimization. We first bridge the uni-modal and multi-modal gap by performing analysis on Image Classification reformulated Visual Question Answering (VQA) benchmarks. Experimental results show that DiGraP consistently outperforms existing baselines across Image Classfication and VQA tasks with discriminative and generative backbones.
  arXiv  Detail & Related papers  (2025-02-21T19:31:55Z)
• Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
  This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. We identify model weaknesses by testing the model using the counterfactual image dataset. We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
  arXiv  Detail & Related papers  (2024-06-19T08:07:14Z)
• Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness [4.339574774938128]
  We present a novel framework for generating adversarial benchmarks to evaluate the robustness of image classification models. Our framework allows users to customize the types of distortions to be optimally applied to images, which helps address the specific distortions relevant to their deployment.
  arXiv  Detail & Related papers  (2023-10-28T07:40:42Z)
• Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters [69.24377241408851]
  Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. We propose to base the selection on gradient-signal-to-noise ratio (GSNR) of network's parameters.
  arXiv  Detail & Related papers  (2023-10-11T10:21:34Z)
• Masked Images Are Counterfactual Samples for Robust Fine-tuning [77.82348472169335]
  Fine-tuning deep learning models can lead to a trade-off between in-distribution (ID) performance and out-of-distribution (OOD) robustness. We propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
  arXiv  Detail & Related papers  (2023-03-06T11:51:28Z)
• CLAD: A Contrastive Learning based Approach for Background Debiasing [43.0296255565593]
  We introduce a contrastive learning-based approach to mitigate the background bias in CNNs. We achieve state-of-the-art results on the Background Challenge dataset, outperforming the previous benchmark with a margin of 4.1%.
  arXiv  Detail & Related papers  (2022-10-06T08:33:23Z)
• Deep Learning-Based Defect Classification and Detection in SEM Images [1.9206693386750882]
  In particular, we train RetinaNet models using different ResNet, VGGNet architectures as backbone. We propose a preference-based ensemble strategy to combine the output predictions from different models in order to achieve better performance on classification and detection of defects.
  arXiv  Detail & Related papers  (2022-06-20T16:34:11Z)
• Face Anti-Spoofing Via Disentangled Representation Learning [90.90512800361742]
  Face anti-spoofing is crucial to security of face recognition systems. We propose a novel perspective of face anti-spoofing that disentangles the liveness features and content features from images.
  arXiv  Detail & Related papers  (2020-08-19T03:54:23Z)
• Depth image denoising using nuclear norm and learning graph model [107.51199787840066]
  Group-based image restoration methods are more effective in gathering the similarity among patches. For each patch, we find and group the most similar patches within a searching window. The proposed method is superior to other current state-of-the-art denoising methods in both subjective and objective criterion.
  arXiv  Detail & Related papers  (2020-08-09T15:12:16Z)
• Deep Semantic Matching with Foreground Detection and Cycle-Consistency [103.22976097225457]
  We address weakly supervised semantic matching based on a deep network. We explicitly estimate the foreground regions to suppress the effect of background clutter. We develop cycle-consistent losses to enforce the predicted transformations across multiple images to be geometrically plausible and consistent.
  arXiv  Detail & Related papers  (2020-03-31T22:38:09Z)

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.