SIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding

• URL: http://arxiv.org/abs/2605.00401v1
• Date: Fri, 01 May 2026 04:43:24 GMT
• Title: SIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding
• Abstract summary: SIMON is a saliency-aware multi-view framework for zero-shot EEG-to-image retrieval.<n>On THINGS-EEG, SIMON achieves state-of-the-art performance in both intra-subject and inter-subject settings.
• Score: 1.491109220586182
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent EEG-to-image retrieval methods leverage pretrained vision encoders and foveation-inspired priors, but typically assume a fixed, center-focused view. This center bias conflicts with content-driven human attention, creating a geometric-semantic dissociation between visual features and EEG responses. We propose SIMON, a saliency-aware multi-view framework for zero-shot EEG-to-image retrieval. SIMON combines foreground segmentation and saliency prediction to select fixation centers via Saliency-Aware Sampling (SAS), then generates foveated views that emphasize informative object regions while suppressing background clutter. On THINGS-EEG, SIMON achieves state-of-the-art performance in both intra-subject and inter-subject settings, reaching an average Top-1 accuracy of 69.7% and 19.6%, respectively, consistently outperforming recent competitive baselines. Analyses across sampling granularity, EEG channel topology, and visual/brain encoder backbones further support the robustness of saliency-aware multi-view integration. Our code and models are publicly available at https://github.com/simonlink666/SIMON.

Related papers

• FSDBN: Foreground-Aware EEG-Visual Alignment via Dynamic Brain Networks [27.513958973574912]
  EEG-based visual decoding provides a non-invasive pathway for interpreting visual semantics.<n>We propose FSDB, a unified framework for robust EEG-visual decoding.<n> FSDB achieves 69.0 percent top-1 accuracy and 92.2 percent top-5 accuracy, outperforming previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-20T07:40:45Z)
• Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning [14.06281700156702]
  We propose a unified framework that integrates language-guided visual reasoning into CT interpretation.<n>Our method introduces task-routing tokens that trigger detection and segmentation heads conditioned on a large vision-language model.<n>To support model training and evaluation, we curated a new multimodal CT dataset.
  arXiv  Detail & Related papers  (2026-05-15T14:27:07Z)
• Subject-Aware Multi-Granularity Alignment for Zero-Shot EEG-to-Image Retrieval [6.9700202682590024]
  We propose a subject-aware multi-granularity alignment (SAMGA) framework for zero-shot EEG-to-image retrieval.<n>SAMGA first constructs a subject-aware visual supervision target by adaptively aggregating multiple intermediate representations from a pretrained vision encoder.<n>Experiments on the THINGS-EEG benchmark demonstrate that the proposed method achieves 91.3% Top-1 and 98.8% Top-5 accuracy in the intra-subject setting, and 34.4% Top-1 and 64.8% Top-5 accuracy in the inter-subject setting.
  arXiv  Detail & Related papers  (2026-04-20T04:10:30Z)
• Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction [47.01100029571904]
  We study the task of establishing object-level visual correspondence across different viewpoints in videos, focusing on the challenging egocentric-to-exocentric and exocentric-to-egocentric scenarios.<n>We propose a simple yet effective framework based on conditional binary segmentation, where an object query mask is encoded into a latent representation to guide the localization of the corresponding object in a target video.<n> Experiments on the Ego-Exo4D and HANDAL-X benchmarks demonstrate the effectiveness of our optimization objective and TTT strategy, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-22T00:53:03Z)
• SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding [0.0]
  This paper proposes a novel framework, named SPORTS, for holistic scene understanding.<n>It integrates Video Panoptic (VPS), Visual Odometry (VO), and Scene Rendering tasks into an iterative and unified perspective.<n>Our attention-based feature fusion outperforms most existing state-of-the-art synthesis methods on the odometry, tracking, segmentation, and novel view tasks.
  arXiv  Detail & Related papers  (2025-10-14T17:28:19Z)
• Complementary and Contrastive Learning for Audio-Visual Segmentation [74.11434759171199]
  We present Complementary and Contrastive Transformer (CCFormer), a novel framework adept at processing both local and global information.<n>Our method sets new state-of-the-art benchmarks across the S4, MS3 and AVSS datasets.
  arXiv  Detail & Related papers  (2025-10-11T06:36:59Z)
• CRIA: A Cross-View Interaction and Instance-Adapted Pre-training Framework for Generalizable EEG Representations [52.251569042852815]
  CRIA is an adaptive framework that utilizes variable-length and variable-channel coding to achieve a unified representation of EEG data across different datasets.<n>The model employs a cross-attention mechanism to fuse temporal, spectral, and spatial features effectively.<n> Experimental results on the Temple University EEG corpus and the CHB-MIT dataset show that CRIA outperforms existing methods with the same pre-training conditions.
  arXiv  Detail & Related papers  (2025-06-19T06:31:08Z)
• Multi-view Aggregation Network for Dichotomous Image Segmentation [76.75904424539543]
  Dichotomous Image (DIS) has recently emerged towards high-precision object segmentation from high-resolution natural images. Existing methods rely on tedious multiple encoder-decoder streams and stages to gradually complete the global localization and local refinement. Inspired by it, we model DIS as a multi-view object perception problem and provide a parsimonious multi-view aggregation network (MVANet) Experiments on the popular DIS-5K dataset show that our MVANet significantly outperforms state-of-the-art methods in both accuracy and speed.
  arXiv  Detail & Related papers  (2024-04-11T03:00:00Z)
• High Pileup Particle Tracking with Object Condensation [7.962871190916326]
  Recent work has demonstrated that graph neural networks (GNNs) can match the performance of traditional algorithms for charged particle tracking. We consider an alternative based on object condensation (OC), a multi-objective learning framework designed to cluster points (hits) belonging to an arbitrary number of objects (tracks) and regress the properties of each object.
  arXiv  Detail & Related papers  (2023-12-06T19:00:00Z)
• ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection [70.11264880907652]
  Recent object (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. We propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and camouflaged zooming in and out. Our framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks.
  arXiv  Detail & Related papers  (2023-10-31T06:11:23Z)
• Salient Objects in Clutter [130.63976772770368]
  This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets. This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets. We propose a new high-quality dataset and update the previous saliency benchmark.
  arXiv  Detail & Related papers  (2021-05-07T03:49:26Z)
• Gradient-Induced Co-Saliency Detection [81.54194063218216]
  Co-saliency detection (Co-SOD) aims to segment the common salient foreground in a group of relevant images. In this paper, inspired by human behavior, we propose a gradient-induced co-saliency detection method.
  arXiv  Detail & Related papers  (2020-04-28T08:40:55Z)
• Object-Centric Image Generation from Layouts [93.10217725729468]
  We develop a layout-to-image-generation method to generate complex scenes with multiple objects. Our method learns representations of the spatial relationships between objects in the scene, which lead to our model's improved layout-fidelity. We introduce SceneFID, an object-centric adaptation of the popular Fr'echet Inception Distance metric, that is better suited for multi-object images.
  arXiv  Detail & Related papers  (2020-03-16T21:40:09Z)

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.