Copertina

An extremely coarse feedback signal is sufficient for learning human-aligned visual representations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mehta, Yash, Bonner, Michael F.
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Universal dimensions of visual representation
di: Chen, Zirui, et al.
Pubblicazione: (2024)

Efficient coding along the visual hierarchy
di: Passi, Ananya, et al.
Pubblicazione: (2026)

Predicting upcoming visual features during eye movements yields scene representations aligned with human visual cortex
di: Thorat, Sushrut, et al.
Pubblicazione: (2025)

Self-supervised video pretraining yields robust and more human-aligned visual representations
di: Parthasarathy, Nikhil, et al.
Pubblicazione: (2022)

Evaluating alignment between humans and neural network representations in image-based learning tasks
di: Demircan, Can, et al.
Pubblicazione: (2023)

Do text-free diffusion models learn discriminative visual representations?
di: Mukhopadhyay, Soumik, et al.
Pubblicazione: (2023)

Visual representations in the human brain are aligned with large language models
di: Doerig, Adrien, et al.
Pubblicazione: (2022)

Can multimodal representation learning by alignment preserve modality-specific information?
di: Thoreau, Romain, et al.
Pubblicazione: (2025)

Characterizing the visual representation of objects from the child's view
di: Yang, Jane, et al.
Pubblicazione: (2026)

Vision Transformer attention alignment with human visual perception in aesthetic object evaluation
di: Carrasco, Miguel, et al.
Pubblicazione: (2025)

Dimensions underlying the representational alignment of deep neural networks with humans
di: Mahner, Florian P., et al.
Pubblicazione: (2024)

Do computer vision foundation models learn the low-level characteristics of the human visual system?
di: Cai, Yancheng, et al.
Pubblicazione: (2025)

Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM study
di: Chamas, Rabih, et al.
Pubblicazione: (2024)

MoDiPO: text-to-motion alignment via AI-feedback-driven Direct Preference Optimization
di: Pappa, Massimiliano, et al.
Pubblicazione: (2024)

Closing the gap in multimodal medical representation alignment
di: Grassucci, Eleonora, et al.
Pubblicazione: (2026)

Towards aligned body representations in vision models
di: Gizdov, Andrey, et al.
Pubblicazione: (2025)

Extending global-local view alignment for self-supervised learning with remote sensing imagery
di: Wanyan, Xinye, et al.
Pubblicazione: (2023)

Self-supervised vision-langage alignment of deep learning representations for bone X-rays analysis
di: Englebert, Alexandre, et al.
Pubblicazione: (2024)

A transition towards virtual representations of visual scenes
di: Pereira, Américo, et al.
Pubblicazione: (2024)

Assessing the alignment between infants' visual and linguistic experience using multimodal language models
di: Tan, Alvin Wei Ming, et al.
Pubblicazione: (2025)

AGA: An adaptive group alignment framework for structured medical cross-modal representation learning
di: Li, Wei, et al.
Pubblicazione: (2025)

Sparse components distinguish visual pathways & their alignment to neural networks
di: Marvi, Ammar I, et al.
Pubblicazione: (2025)

Learning complete and explainable visual representations from itemized text supervision
di: Lyu, Yiwei, et al.
Pubblicazione: (2025)

On the dynamic evolution of CLIP texture-shape bias and its relationship to human alignment and model robustness
di: Hernández-Cámara, Pablo, et al.
Pubblicazione: (2025)

A Self supervised learning framework for imbalanced medical imaging datasets
di: Sharma, Yash Kumar, et al.
Pubblicazione: (2026)

CoCoG-2: Controllable generation of visual stimuli for understanding human concept representation
di: Wei, Chen, et al.
Pubblicazione: (2024)

Generating visual explanations from deep networks using implicit neural representations
di: Byra, Michal, et al.
Pubblicazione: (2025)

Self-supervised structured object representation learning
di: Hadjerci, Oussama, et al.
Pubblicazione: (2025)

Deep video representation learning: a survey
di: Ravanbakhsh, Elham, et al.
Pubblicazione: (2024)

A deep multiple instance learning approach based on coarse labels for high-resolution land-cover mapping
di: Perantoni, Gianmarco, et al.
Pubblicazione: (2025)

Pathological Truth Bias in Vision-Language Models
di: Thube, Yash
Pubblicazione: (2025)

Noise-aware few-shot learning through bi-directional multi-view prompt alignment
di: Niu, Lu, et al.
Pubblicazione: (2026)

UniAR: A Unified model for predicting human Attention and Responses on visual content
di: Li, Peizhao, et al.
Pubblicazione: (2023)

Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations
di: Xie, Yudi, et al.
Pubblicazione: (2024)

Affine transformation estimation improves visual self-supervised learning
di: Torpey, David, et al.
Pubblicazione: (2024)

Human alignment of neural network representations
di: Muttenthaler, Lukas, et al.
Pubblicazione: (2022)

CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback
di: Hein, Dennis, et al.
Pubblicazione: (2024)

KBody: Towards general, robust, and aligned monocular whole-body estimation
di: Zioulis, Nikolaos, et al.
Pubblicazione: (2023)

Video alignment using unsupervised learning of local and global features
di: Fakhfour, Niloufar, et al.
Pubblicazione: (2023)

Bridging the gap to real-world language-grounded visual concept learning
di: Jung, Whie, et al.
Pubblicazione: (2025)