D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition

• URL: http://arxiv.org/abs/2504.06432v2
• Date: Fri, 11 Apr 2025 14:50:12 GMT
• Title: D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition
• Authors: Rupayan Mallick, Sibo Dong, Nataniel Ruiz, Sarah Adel Bargal,
• Abstract summary: This paper proposes a pipeline that utilizes a frozen diffusion model.<n>We hypothesize that such features can help hallucinate object visual features behind occluding objects.<n>We demonstrate that our proposed use of diffusion-based features results in models that are more robust to partial object occlusions.
• Score: 13.854486943187565
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Applications of diffusion models for visual tasks have been quite noteworthy. This paper targets making classification models more robust to occlusions for the task of object recognition by proposing a pipeline that utilizes a frozen diffusion model. Diffusion features have demonstrated success in image generation and image completion while understanding image context. Occlusion can be posed as an image completion problem by deeming the pixels of the occluder to be `missing.' We hypothesize that such features can help hallucinate object visual features behind occluding objects, and hence we propose using them to enable models to become more occlusion robust. We design experiments to include input-based augmentations as well as feature-based augmentations. Input-based augmentations involve finetuning on images where the occluder pixels are inpainted, and feature-based augmentations involve augmenting classification features with intermediate diffusion features. We demonstrate that our proposed use of diffusion-based features results in models that are more robust to partial object occlusions for both Transformers and ConvNets on ImageNet with simulated occlusions. We also propose a dataset that encompasses real-world occlusions and demonstrate that our method is more robust to partial object occlusions.

Related papers

• Are Deep Learning Models Robust to Partial Object Occlusion in Visual Recognition Tasks? [4.9260675787714]
  Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under partial occlusion. We contribute the Image Recognition Under Occlusion (IRUO) dataset, based on the recently developed Occluded Video Instance (IRUO) dataset (arXiv:2102.01558) We find that modern CNN-based models show improved recognition accuracy on occluded images compared to earlier CNN-based models, and ViT-based models are more accurate than CNN-based models on occluded images.
  arXiv  Detail & Related papers  (2024-09-16T23:21:22Z)
• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• Diffusion Model for Camouflaged Object Detection [2.592600158870236]
  We propose a diffusion-based framework for camouflaged object detection, termed diffCOD. The proposed method achieves favorable performance compared to the existing 11 state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-08-01T05:50:33Z)
• Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence [88.00004819064672]
  Diffusion Hyperfeatures is a framework for consolidating multi-scale and multi-timestep feature maps into per-pixel feature descriptors. Our method achieves superior performance on the SPair-71k real image benchmark.
  arXiv  Detail & Related papers  (2023-05-23T17:58:05Z)
• Feature Completion Transformer for Occluded Person Re-identification [25.159974510754992]
  Occluded person re-identification (Re-ID) is a challenging problem due to the destruction of occluders. We propose a Feature Completion Transformer (FCFormer) to implicitly complement the semantic information of occluded parts in the feature space. FCFormer achieves superior performance and outperforms the state-of-the-art methods by significant margins on occluded datasets.
  arXiv  Detail & Related papers  (2023-03-03T01:12:57Z)
• Person Image Synthesis via Denoising Diffusion Model [116.34633988927429]
  We show how denoising diffusion models can be applied for high-fidelity person image synthesis. Our results on two large-scale benchmarks and a user study demonstrate the photorealism of our proposed approach under challenging scenarios.
  arXiv  Detail & Related papers  (2022-11-22T18:59:50Z)
• DisPositioNet: Disentangled Pose and Identity in Semantic Image Manipulation [83.51882381294357]
  DisPositioNet is a model that learns a disentangled representation for each object for the task of image manipulation using scene graphs. Our framework enables the disentanglement of the variational latent embeddings as well as the feature representation in the graph.
  arXiv  Detail & Related papers  (2022-11-10T11:47:37Z)
• High-resolution Iterative Feedback Network for Camouflaged Object Detection [128.893782016078]
  Spotting camouflaged objects that are visually assimilated into the background is tricky for object detection algorithms. We aim to extract the high-resolution texture details to avoid the detail degradation that causes blurred vision in edges and boundaries. We introduce a novel HitNet to refine the low-resolution representations by high-resolution features in an iterative feedback manner.
  arXiv  Detail & Related papers  (2022-03-22T11:20:21Z)
• Blur-Attention: A boosting mechanism for non-uniform blurred image restoration [27.075713246257596]
  We propose a blur-attention module to dynamically capture the spatially varying features of non-uniform blurred images. By introducing the blur-attention network into a conditional generation adversarial framework, we propose an end-to-end blind motion deblurring method. Experimental results show that the deblurring capability of our method achieved outstanding objective performance in terms of PSNR, SSIM, and subjective visual quality.
  arXiv  Detail & Related papers  (2020-08-19T16:07:06Z)
• Saliency-driven Class Impressions for Feature Visualization of Deep Neural Networks [55.11806035788036]
  It is advantageous to visualize the features considered to be essential for classification. Existing visualization methods develop high confidence images consisting of both background and foreground features. In this work, we propose a saliency-driven approach to visualize discriminative features that are considered most important for a given task.
  arXiv  Detail & Related papers  (2020-07-31T06:11:06Z)

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.