Visual perception and processing mechanisms

Neueste Paper

• CPrefix: A Combinatorial Tensor Framework for Structured Discrete Color Mappings

  Yvan Richard · 5. August 2026

  Discrete multi-channel mappings are typically represented through sampled values, providing accurate evaluations but limited insight into their underlying structure. We introduce CPrefix, a combinatorial observable representation for discrete mappings, realized within a unified tensor framework that…

• Do Vision Encoders Exhibit Human-like Color Thresholds?

  Engy Ehab, Pablo Hernández-Cámara, Nahla Belal, Jesús Malo, Javier Vazquez-Corral, Alexandra Gomez-Villa · 21. Juli 2026

  Understanding and characterizing human color perception is a longstanding research goal. One of the most traditional approaches is looking for the human color discrimination thresholds, the minimum chromatic differences perceptible to human observers. In recent years, deep neural networks have becom…

• Toward a mechanistic understanding of inference in visual cortex and diffusion models

  Zeyu Yun, Alexander Belsten, Dasheng Bi, Zahra Kadkhodaie, Yubei Chen, Bruno A. Olshausen · 20. Juli 2026

  We describe a model of perceptual inference in primary visual cortex (V1) equivalent to a minimal diffusion model whose function can be readily understood from its parameters. The model is based on sparse coding with a non-factorial prior over latent variables in the form of an unconstrained, pairwi…

• What Color is the Sky (for a non-human) ?

  Yair Weiss, Ofer Springer · 30. Juni 2026

  The light of the daytime sky contains a mixture of many colors yet is perceived as blue by human observers. This is largely due to the particular response functions of the human cones. Under these response functions skylight and blue light are metamers: they yield the exact same excitation of the co…

• NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning

  Tianlin Pan, Lianyu Pang, Cheng Da, Huan Yang, Changqian Yu, Kun Gai, Wenhan Luo · 29. Juni 2026

  Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not captured by the reward proxy. We identify a simple structural signature of this drift: across three post-training methods (NFT, AWM, DPO), RL f…

• Inducing Spatial Locality in Vision Transformers through the Training Protocol

  Eduardo Santiago Toledo, Asael Fabian Mart\'inez · 19. Mai 2026

  We investigate whether the training protocol can induce spatial locality in the early layers of a Vision Transformer (ViT) trained from scratch, without large-scale pretraining. Keeping the architecture and optimization procedure fixed, we compare a Baseline protocol with a Modern protocol (AutoAugm…

• Attention Transfer Is Not Universally Effective for Vision Transformers

  Huaiyuan Qin, Muli Yang, Gabriel James Goenawan, Peng Hu, Chen Gong, Xi Peng, Hongyuan Zhu · 11. Mai 2026

  A recent work shows that Attention Transfer, which transfers only the attention patterns from a pre-trained teacher Vision Transformer (ViT) to a randomly initialized standard student ViT, is sufficient to recover the full benefit of the teacher's pre-trained weights. We revisit this finding on a co…

• From Edges to Depth: Probing the Spatial Hierarchy in Vision Transformers

  Jainum Sanghavi · 28. April 2026

  Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded. Probing a frozen ViT-B/16 layerwise for two complementary prope…

• Rank, Head-Channel Non-Identifiability, and Symmetry Breaking: A Precise Analysis of Representational Collapse in Transformers

  Giansalvo Cirrincione · 28. April 2026

  A widely cited result by Dong et al. (2021) showed that Transformers built from self-attention alone, without skip connections or feed-forward layers, suffer from rapid rank collapse: all token representations converge to a single direction. The proposed remedy was the MLP. We show that this picture…

• Bio-inspired Color Constancy: From Gray Anchoring Theory to Gray Pixel Methods

  Kai-Fu Yang, Fu-Ya Luo, Yong-Jie Li · 23. April 2026

  Color constancy is a fundamental ability of many biological visual systems and a crucial step in computer imaging systems. Bio-inspired modeling offers a promising way to elucidate the computational principles underlying color constancy and to develop efficient computational methods. However, bio-in…

• Do vision models perceive illusory motion in static images like humans?

  Isabella Elaine Rosario, Fan L. Cheng, Zitang Sun, Nikolaus Kriegeskorte · 14. April 2026

  Understanding human motion processing is essential for building reliable, human-centered computer vision systems. Although deep neural networks (DNNs) achieve strong performance in optical flow estimation, they remain less robust than humans and rely on fundamentally different computational strategi…

• Perceptual misalignment of texture representations in convolutional neural networks

  Ludovica de Paolis, Fabio Anselmi, Alessio Ansuini, Eugenio Piasini · 3. April 2026

  Mathematical modeling of visual textures traces back to Julesz's intuition that texture perception in humans is based on local correlations between image features. An influential approach for texture analysis and generation generalizes this notion to linear correlations between the nonlinear feature…

• Bioinspired CNNs for border completion in occluded images

  Catarina P. Coutinho, Aneeqa Merhab, Janko Petkovic, Ferdinando Zanchetta, Rita Fioresi · 12. März 2026

  We exploit the mathematical modeling of the border completion problem in the visual cortex to design convolutional neural network (CNN) filters that enhance robustness to image occlusions. We evaluate our CNN architecture, BorderNet, on three occluded datasets (MNIST, Fashion-MNIST, and EMNIST) unde…

• Locating and Editing Figure-Ground Organization in Vision Transformers

  Stefan Arnold, René Gröbner · 9. März 2026

  Vision Transformers must resolve figure-ground organization by choosing between completions driven by local geometric evidence and those favored by global organizational priors, giving rise to a characteristic perceptual ambiguity. We aim to locate where the canonical Gestalt prior convexity is real…

• OWL: A Novel Approach to Machine Perception During Motion

  Daniel Raviv, Juan D. Yepes · 9. März 2026

  We introduce a perception-related function, OWL, designed to address the complex challenges of 3D perception during motion. It derives its values directly from two fundamental visual motion cues, with one set of cue values per point per time instant. During motion, two visual motion cues relative to…

• Effects of the retina-inspired light intensity encoding on color discrimination performance

  Io Yamada, Hirotsugu Okuno · 20. Januar 2026

  Color is an important source of information for visual functions such as object recognition, but it is greatly affected by the color of illumination. The ability to perceive the color of a visual target independent of illumination color is called color constancy (CC), and is an important feature for…

• Transformers self-organize like newborn visual systems when trained in prenatal worlds

  Lalit Pandey, Samantha M. W. Wood, Justin N. Wood · 7. Januar 2026

  Do transformers learn like brains? A key challenge in addressing this question is that transformers and brains are trained on fundamentally different data. Brains are initially "trained" on prenatal sensory experiences (e.g., retinal waves), whereas transformers are typically trained on large datase…

• Credit Assignment via Neural Manifold Noise Correlation

  Byungwoo Kang, Maceo Richards, Bernardo Sabatini · 7. Januar 2026

  Credit assignment--how changes in individual neurons and synapses affect a network's output--is central to learning in brains and machines. Noise correlation, which estimates gradients by correlating perturbations of activity with changes in output, provides a biologically plausible solution to cred…

• Block-Recurrent Dynamics in Vision Transformers

  Mozes Jacobs, Thomas Fel, Richard Hakim, Alessandra Brondetta, Demba Ba, T. Andy Keller · 24. Dezember 2025

  As Vision Transformers (ViTs) become standard vision backbones, a mechanistic account of their computational phenomenology is essential. Despite architectural cues that hint at dynamical structure, there is no settled framework that interprets Transformer depth as a well-characterized flow. In this …

• Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream

  Abdulkadir Gokce, Martin Schrimpf · 7. November 2025

  When trained on large-scale object classification datasets, certain artificial neural network models begin to approximate core object recognition behaviors and neural response patterns in the primate brain. While recent machine learning advances suggest that scaling compute, model size, and dataset …