From Preimage Search To Source-Grounded Feature Inversion

• URL: http://arxiv.org/abs/2607.12526v1
• Date: Tue, 14 Jul 2026 09:02:41 GMT
• Title: From Preimage Search To Source-Grounded Feature Inversion
• Abstract summary: We formulate source-grounded feature inversion by conditioning the inverse on the source-local network geometry at the target-generating input.<n>One calibrated zero-intercept map family supports new inputs, depths, channels, and channel groups across diverse CNN and Transformer architectures.<n> Prediction-conditioned feature atlases align these visualisations with independent interventions on the corresponding internal features.
• Score: 0.33842793760651557
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Interpreting a neural network requires understanding what its internal features extract from a particular input. Feature inversion seeks to express a selected feature in the input domain, but canonical iterative methods search for an input whose re-encoded representation matches the target. Because many inputs can satisfy this constraint, target matching alone does not specify the inverse associated with the sample that generated the feature. We formulate source-grounded feature inversion by conditioning the inverse on the source-local network geometry at the target-generating input. At each boundary of the computational DAG, backpropagation provides the correct reverse dependencies but transports an adjoint signal rather than an upstream-state estimate. We locally repair this signal with a closed-form matrix Wiener map from a mean-seed VJP to the upstream state, followed by a second Wiener map for the JVP forward-consistency residual, and compose the repaired states through the same DAG in one finite reverse pass. One calibrated zero-intercept map family supports new inputs, depths, channels, and channel groups across diverse CNN and Transformer architectures, tensor components, and visual distributions without query-specific optimisation. Matched target and source controls verify that each inverse depends on the selected feature and the local operators of the sample being explained, rather than a target-independent image template. Prediction-conditioned feature atlases align these visualisations with independent interventions on the corresponding internal features. Together, source-grounded feature inversion opens the model's hidden feature hierarchy to inspection at the level of individual layers and channels, linking what the network extracts from an input to the internal evidence that shapes its decision.

Related papers

• Attribution via Distributional Paths for Information Revelation [2.707154152696381]
  Our method Reveal-IG lifts path attribution from input space to a space of structured probe distributions.<n>It produces stable, signed attributions -- leading to metrics that use attribution sign while remaining competitive on the rest.
  arXiv  Detail & Related papers  (2026-06-02T16:50:28Z)
• Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach [60.199985286210904]
  Generalist graph anomaly detection (GAD) aims to detect anomalies on unseen graphs without graph-specific retraining.<n>Existing approaches primarily focus on aligning heterogeneous data across domains, which ignores different feature semantics.<n>We propose Fingerprint-based generalist GAD approach (ReFi-GAD)<n>We show that ReFi-GAD significantly outperforms state-of-the-art methods in experiments on 14 datasets.
  arXiv  Detail & Related papers  (2026-05-25T05:12:26Z)
• Joint-Optimized Unsupervised Adversarial Domain Adaptation in Remote Sensing Segmentation with Prompted Foundation Model [32.03242732902217]
  This paper addresses the challenge of adapting a model trained on source domain data to target domain samples. We propose a joint-optimized adversarial network incorporating the "Segment Anything Model (SAM) (SAM-JOANet)"
  arXiv  Detail & Related papers  (2024-11-08T02:15:20Z)
• Interpreting the Residual Stream of ResNet18 [0.0]
  This work investigates ResNet18 with a particular focus on its residual stream, an architectural mechanism which InceptionV1 lacks. We show that many residual stream channels compute scale invariant representations through a mixture of the input's smaller-scale feature with the block's larger-scale feature.
  arXiv  Detail & Related papers  (2024-07-07T12:13:03Z)
• A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling [54.05517338122698]
  A popular similarity-based feature upsampling pipeline has been proposed, which utilizes a high-resolution feature as guidance.<n>We propose an explicitly controllable query-key feature alignment from both semantic-aware and detail-aware perspectives.<n>We develop a fine-grained neighbor selection strategy on HR features, which is simple yet effective for alleviating mosaic artifacts.
  arXiv  Detail & Related papers  (2024-07-02T14:12:21Z)
• An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning [0.46644955105516456]
  Zero-shot Learning (ZSL) classification categorizes or predicts classes (labels) that are not included in the training set (unseen classes) Recent works proposed different semantic autoencoder (SAE) models where the encoder embeds a visual feature space into the semantic space and the decoder reconstructs the original visual feature space. We propose an integral projection-based semantic autoencoder (IP-SAE) where an encoder projects a visual feature space vectord with the semantic space into a latent representation space.
  arXiv  Detail & Related papers  (2023-06-26T12:06:20Z)
• Hybrid Routing Transformer for Zero-Shot Learning [83.64532548391]
  This paper presents a novel transformer encoder-decoder model, called hybrid routing transformer (HRT) We embed an active attention, which is constructed by both the bottom-up and the top-down dynamic routing pathways to generate the attribute-aligned visual feature. While in HRT decoder, we use static routing to calculate the correlation among the attribute-aligned visual features, the corresponding attribute semantics, and the class attribute vectors to generate the final class label predictions.
  arXiv  Detail & Related papers  (2022-03-29T07:55:08Z)
• Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection [85.11649974840758]
  3D object detection networks tend to be biased towards the data they are trained on. We propose a single-frame approach for source-free, unsupervised domain adaptation of lidar-based 3D object detectors.
  arXiv  Detail & Related papers  (2021-11-30T18:42:42Z)
• MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking [72.65494220685525]
  We propose a new dynamic modality-aware filter generation module (named MFGNet) to boost the message communication between visible and thermal data. We generate dynamic modality-aware filters with two independent networks. The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively. To address issues caused by heavy occlusion, fast motion, and out-of-view, we propose to conduct a joint local and global search by exploiting a new direction-aware target-driven attention mechanism.
  arXiv  Detail & Related papers  (2021-07-22T03:10:51Z)
• The DEformer: An Order-Agnostic Distribution Estimating Transformer [17.352818121007576]
  Order-agnostic autoregressive distribution estimation (OADE) is a challenging problem in generative machine learning. We propose an alternative approach for encoding feature identities, where each feature's identity is included alongside its value in the input. We show that a Transformer trained on this input can effectively model binarized-MNIST, approaching the average negative log-likelihood of fixed order autoregressive distribution estimating algorithms.
  arXiv  Detail & Related papers  (2021-06-13T13:33:31Z)
• Volumetric Transformer Networks [88.85542905676712]
  We introduce a learnable module, the volumetric transformer network (VTN) VTN predicts channel-wise warping fields so as to reconfigure intermediate CNN features spatially and channel-wisely. Our experiments show that VTN consistently boosts the features' representation power and consequently the networks' accuracy on fine-grained image recognition and instance-level image retrieval.
  arXiv  Detail & Related papers  (2020-07-18T14:00:12Z)

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.