Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers

• URL: http://arxiv.org/abs/2605.08188v1
• Date: Tue, 05 May 2026 12:45:27 GMT
• Title: Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers
• Abstract summary: The concept of visual interest was examined within the multimodal vision-language-model Qwen3-VL-8B.<n>We analyzed internal representations across vision and language components using methods from the neurosciences.
• Score: 3.07869141026886
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Human attention is the gateway to conscious perception, memory and decision-making. However, its role in modern transformer models remains largely unexplored. As these systems increasingly influence what people see, prefer and buy, the question arises as to whether they encode principles of human interest or merely exploit large-scale correlations. Addressing this issue is crucial for understanding cognition and ensuring the responsible use of AI in communication and marketing. In order to address this issue, the concept of visual interest was examined within the multimodal vision-language-model Qwen3-VL-8B, using a pre-defined Common Interestingness (CI) score derived from large-scale human engagement data on the photo-sharing platform Flickr. Here, we analyzed internal representations across vision and language components using methods from the neurosciences. Our analyses revealed that CI information is linearly decodable from final-layer embeddings, indicating that it is aligned with human-derived measures of visual interestingness. Dimensionality reduction and Generalized Discrimination Value (GDV) analyses demonstrate that CI-related hidden representations emerge in intermediate vision transformer layers and becomes progressively more distinguishable across language model layers. Concept vectors derived using geometric, probe, and Sparse Auto-Encoder based methods converge in higher layers, as confirmed by representational similarity analysis. This indicates a robust and structured encoding of visual interestingness without explicit supervision. Future work will seek to identify shared computational principles linking human brain dynamics and transformer architectures, with the ultimate goal of uncovering the organizing mechanisms that give rise to attention and interest in both biological and artificial systems.

Related papers

• Commonsense Reasoning in Computer Vision: Foundations, Recent Advancements, and Future Directions [1.396778199498531]
  This paper presents a survey of developments that integrate commonsense knowledge into computer vision tasks.<n>We discuss current limitations related to dataset bias, knowledge incompleteness, and integration challenges.<n>We highlight prospective research trajectories in cross-modal reasoning, scalable commonsense knowledge injection, and neuro-symbolic hybrid architectures.
  arXiv  Detail & Related papers  (2026-09-04T15:19:37Z)
• An extremely coarse feedback signal is sufficient for learning human-aligned visual representations [2.9506547907696006]
  We investigate how the coarseness of a learning signal shapes representational alignment with human vision.<n>We train hundreds of neural networks across convolutional and transformer architectures on these coarse classification tasks.<n>We find that networks trained to distinguish as few as 8 broad categories learn representations that match or exceed the neural alignment of models distinguishing 1,000-classes.
  arXiv  Detail & Related papers  (2026-05-07T01:02:21Z)
• Causal Interpretation of Neural Network Computations with Contribution Decomposition [13.992892699439023]
  We take a direct approach to examine how hidden neurons act to drive network outputs.<n>We introduce CODEC, a method that uses sparse autoencoders to decompose network behavior into sparse motifs of hidden-neuron contributions.
  arXiv  Detail & Related papers  (2026-03-06T18:46:06Z)
• Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning [56.24016465596292]
  A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric.<n>We introduce the task of Visual Metaphor Transfer (VMT), which challenges models to autonomously decouple the "creative essence" from a reference image and re-materialize that abstract logic onto a user-specified subject.<n>Our method significantly outperforms SOTA baselines in metaphor consistency, analogy appropriateness, and visual creativity, paving the way for automated high-impact creative applications in advertising and media.
  arXiv  Detail & Related papers  (2026-02-01T17:01:36Z)
• Learning Human-Object Interaction as Groups [52.28258599873394]
  GroupHOI is a framework that propagates contextual information in terms of geometric proximity and semantic similarity.<n>It exhibits leading performance on the more challenging Nonverbal Interaction Detection task.
  arXiv  Detail & Related papers  (2025-10-21T07:25:10Z)
• Convergent transformations of visual representation in brains and models [0.0]
  A fundamental question in cognitive neuroscience is what shapes visual perception: the external world's structure or the brain's internal architecture.<n>We show a convergent computational solution for visual encoding in both human and artificial vision, driven by the structure of the external world.
  arXiv  Detail & Related papers  (2025-07-18T14:13:54Z)
• Concept-Guided Interpretability via Neural Chunking [64.6429903327095]
  We show that neural networks exhibit patterns in their raw population activity that mirror regularities in the training data.<n>We propose three methods to extract recurring chunks on a neural population level.<n>Our work points to a new direction for interpretability, one that harnesses both cognitive principles and the structure of naturalistic data.
  arXiv  Detail & Related papers  (2025-05-16T13:49:43Z)
• Mechanistic understanding and validation of large AI models with SemanticLens [13.712668314238082]
  Unlike human-engineered systems such as aeroplanes, the inner workings of AI models remain largely opaque.<n>This paper introduces SemanticLens, a universal explanation method for neural networks that maps hidden knowledge encoded by components.
  arXiv  Detail & Related papers  (2025-01-09T17:47:34Z)
• Neural Clustering based Visual Representation Learning [61.72646814537163]
  Clustering is one of the most classic approaches in machine learning and data analysis. We propose feature extraction with clustering (FEC), which views feature extraction as a process of selecting representatives from data. FEC alternates between grouping pixels into individual clusters to abstract representatives and updating the deep features of pixels with current representatives.
  arXiv  Detail & Related papers  (2024-03-26T06:04:50Z)
• Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models [56.257840490146]
  ConCue is a novel approach for improving visual feature extraction in HOI detection. We develop a transformer-based feature extraction module with a multi-tower architecture that integrates contextual cues into both instance and interaction detectors.
  arXiv  Detail & Related papers  (2023-11-26T09:11:32Z)
• Neural-Logic Human-Object Interaction Detection [67.4993347702353]
  We present L OGIC HOI, a new HOI detector that leverages neural-logic reasoning and Transformer to infer feasible interactions between entities. Specifically, we modify the self-attention mechanism in vanilla Transformer, enabling it to reason over the human, action, object> triplet and constitute novel interactions. We formulate these two properties in first-order logic and ground them into continuous space to constrain the learning process of our approach, leading to improved performance and zero-shot generalization capabilities.
  arXiv  Detail & Related papers  (2023-11-16T11:47:53Z)
• Deep Co-Attention Network for Multi-View Subspace Learning [73.3450258002607]
  We propose a deep co-attention network for multi-view subspace learning. It aims to extract both the common information and the complementary information in an adversarial setting. In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation.
  arXiv  Detail & Related papers  (2021-02-15T18:46:44Z)
• Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations [103.00383924074585]
  Visual relationship detection aims to reason over relationships among salient objects in images. We propose a novel approach named Visual-Linguistic Representations from Transformers (RVL-BERT) RVL-BERT performs spatial reasoning with both visual and language commonsense knowledge learned via self-supervised pre-training.
  arXiv  Detail & Related papers  (2020-09-10T16:15:09Z)

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.