Inherently Faithful Attention Maps for Vision Transformers

• URL: http://arxiv.org/abs/2506.08915v3
• Date: Tue, 17 Jun 2025 13:45:06 GMT
• Title: Inherently Faithful Attention Maps for Vision Transformers
• Authors: Ananthu Aniraj, Cassio F. Dantas, Dino Ienco, Diego Marcos,
• Abstract summary: We introduce an attention-based method that uses learned binary attention masks to ensure that only attended image regions influence the prediction.<n>Experiments demonstrate that our approach significantly improves robustness against spurious correlations and out-of-distribution backgrounds.
• Score: 7.4774909520731425
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce an attention-based method that uses learned binary attention masks to ensure that only attended image regions influence the prediction. Context can strongly affect object perception, sometimes leading to biased representations, particularly when objects appear in out-of-distribution backgrounds. At the same time, many image-level object-centric tasks require identifying relevant regions, often requiring context. To address this conundrum, we propose a two-stage framework: stage 1 processes the full image to discover object parts and identify task-relevant regions, while stage 2 leverages input attention masking to restrict its receptive field to these regions, enabling a focused analysis while filtering out potentially spurious information. Both stages are trained jointly, allowing stage 2 to refine stage 1. Extensive experiments across diverse benchmarks demonstrate that our approach significantly improves robustness against spurious correlations and out-of-distribution backgrounds. Code: https://github.com/ananthu-aniraj/ifam

Related papers

• OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval [59.377821673653436]
  Composed Image Retrieval (CIR) is capable of expressing users' intricate retrieval requirements flexibly.<n>CIR remains in its nascent stages due to two limitations: 1) inhomogeneity between dominant and noisy portions in visual data is ignored, leading to query feature degradation.<n>This work presents a focus mapping-based feature extractor, which consists of two modules: dominant portion segmentation and dual focus mapping.
  arXiv  Detail & Related papers  (2025-07-08T03:27:46Z)
• Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning [50.88504784466931]
  Multi-task dense prediction involves semantic segmentation, depth estimation, and surface normal estimation. Existing solutions typically rely on learning global image representations for global cross-task image matching. Our proposal involves modeling region-wise representations using Gaussian Distributions.
  arXiv  Detail & Related papers  (2024-03-15T12:41:30Z)
• Learning to search for and detect objects in foveal images using deep learning [3.655021726150368]
  This study employs a fixation prediction model that emulates human objective-guided attention of searching for a given class in an image. The foveated pictures at each fixation point are then classified to determine whether the target is present or absent in the scene. We present a novel dual task model capable of performing fixation prediction and detection simultaneously, allowing knowledge transfer between the two tasks.
  arXiv  Detail & Related papers  (2023-04-12T09:50:25Z)
• Progressively Dual Prior Guided Few-shot Semantic Segmentation [57.37506990980975]
  Few-shot semantic segmentation task aims at performing segmentation in query images with a few annotated support samples. We propose a progressively dual prior guided few-shot semantic segmentation network.
  arXiv  Detail & Related papers  (2022-11-20T16:19:47Z)
• Point-Level Region Contrast for Object Detection Pre-Training [147.47349344401806]
  We present point-level region contrast, a self-supervised pre-training approach for the task of object detection. Our approach performs contrastive learning by directly sampling individual point pairs from different regions. Compared to an aggregated representation per region, our approach is more robust to the change in input region quality.
  arXiv  Detail & Related papers  (2022-02-09T18:56:41Z)
• Leveraging in-domain supervision for unsupervised image-to-image translation tasks via multi-stream generators [4.726777092009554]
  We introduce two techniques to incorporate this invaluable in-domain prior knowledge for the benefit of translation quality. We propose splitting the input data according to semantic masks, explicitly guiding the network to different behavior for the different regions of the image. In addition, we propose training a semantic segmentation network along with the translation task, and to leverage this output as a loss term that improves robustness.
  arXiv  Detail & Related papers  (2021-12-30T15:29:36Z)
• Detect and Locate: A Face Anti-Manipulation Approach with Semantic and Noise-level Supervision [67.73180660609844]
  We propose a conceptually simple but effective method to efficiently detect forged faces in an image. The proposed scheme relies on a segmentation map that delivers meaningful high-level semantic information clues about the image. The proposed model achieves state-of-the-art detection accuracy and remarkable localization performance.
  arXiv  Detail & Related papers  (2021-07-13T02:59:31Z)
• Instance-aware Remote Sensing Image Captioning with Cross-hierarchy Attention [11.23821696220285]
  spatial attention is a straightforward approach to enhance the performance for remote sensing image captioning. We propose a remote sensing image caption generator with instance-awareness and cross-hierarchy attention.
  arXiv  Detail & Related papers  (2021-05-11T12:59:07Z)
• Self-supervised Segmentation via Background Inpainting [96.10971980098196]
  We introduce a self-supervised detection and segmentation approach that can work with single images captured by a potentially moving camera. We exploit a self-supervised loss function that we exploit to train a proposal-based segmentation network. We apply our method to human detection and segmentation in images that visually depart from those of standard benchmarks and outperform existing self-supervised methods.
  arXiv  Detail & Related papers  (2020-11-11T08:34:40Z)
• Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter [62.26677215668959]
  We propose a lightweight, weakly supervised deep network to coarsely locate semantically salient regions. We then fuse multiple off-the-shelf deep models on these semantically salient regions as the pixel-wise saliency refinement. Our method is simple yet effective, which is the first attempt to consider the salient object detection mainly as an object-level semantic re-ranking problem.
  arXiv  Detail & Related papers  (2020-08-10T07:12:43Z)
• Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation [128.03739769844736]
  Two neural co-attentions are incorporated into the classifier to capture cross-image semantic similarities and differences. In addition to boosting object pattern learning, the co-attention can leverage context from other related images to improve localization map inference. Our algorithm sets new state-of-the-arts on all these settings, demonstrating well its efficacy and generalizability.
  arXiv  Detail & Related papers  (2020-07-03T21:53:46Z)

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.