Cover Image

Learned feature representations are biased by complexity, learning order, position, and more

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lampinen, Andrew Kyle, Chan, Stephanie C. Y., Hermann, Katherine
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Representation biases: will we achieve complete understanding by analyzing representations?
by: Lampinen, Andrew Kyle, et al.
Published: (2025)

The in-context inductive biases of vision-language models differ across modalities
by: Allen, Kelsey, et al.
Published: (2025)

On the Foundations of Shortcut Learning
by: Hermann, Katherine L., et al.
Published: (2023)

Understanding Visual Feature Reliance through the Lens of Complexity
by: Fel, Thomas, et al.
Published: (2024)

Personalized federated learning based on feature fusion
by: Xing, Wolong, et al.
Published: (2024)

Decoupling the components of geometric understanding in Vision Language Models
by: Kosoy, Eliza, et al.
Published: (2025)

Spectral regularization for adversarially-robust representation learning
by: Yang, Sheng, et al.
Published: (2024)

On the importance of cross-task features for class-incremental learning
by: Soutif--Cormerais, Albin, et al.
Published: (2021)

Optimization of Precipitate Segmentation Through Linear Genetic Programming of Image Processing
by: Williams, Kyle, et al.
Published: (2026)

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

Understanding normalization in contrastive representation learning and out-of-distribution detection
by: Le-Gia, Tai, et al.
Published: (2023)

Context Sensitivity Improves Human-Machine Visual Alignment
by: Born, Frieda, et al.
Published: (2026)

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

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
by: He, Xilin, et al.
Published: (2024)

Higher order PCA-like rotation-invariant features for detailed shape descriptors modulo rotation
by: Duda, Jarek
Published: (2026)

A training regime to learn unified representations from complementary breast imaging modalities
by: Sharma, Umang, et al.
Published: (2024)

The broader spectrum of in-context learning
by: Lampinen, Andrew Kyle, et al.
Published: (2024)

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

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
by: Burgert, Tom, et al.
Published: (2025)

Task-conditioned adaptation of visual features in multi-task policy learning
by: Marza, Pierre, et al.
Published: (2024)

A self-supervised framework for learning whole slide representations
by: Hou, Xinhai, et al.
Published: (2024)

Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
by: Rypeść, Grzegorz, et al.
Published: (2024)

Learning Conformal Explainers for Image Classifiers
by: Alkhatib, Amr, et al.
Published: (2025)

Hidden in plain sight: VLMs overlook their visual representations
by: Fu, Stephanie, et al.
Published: (2025)

AugLoss: A Robust Augmentation-based Fine Tuning Methodology
by: Otstot, Kyle, et al.
Published: (2022)

Fading memory as inductive bias in residual recurrent networks
by: Dubinin, Igor, et al.
Published: (2023)

FeatMap: Understanding image manipulation in the feature space and its implications for feature space geometry
by: Krey, Elias B., et al.
Published: (2026)

Made to Order: Discovering monotonic temporal changes via self-supervised video ordering
by: Yang, Charig, et al.
Published: (2024)

Aligning Machine and Human Visual Representations across Abstraction Levels
by: Muttenthaler, Lukas, et al.
Published: (2024)

Visual Adaptive Prompting for Compositional Zero-Shot Learning
by: Stein, Kyle, et al.
Published: (2025)

Towards more transferable adversarial attack in black-box manner
by: Lei, Chun Tong, et al.
Published: (2025)

DPA: A one-stop metric to measure bias amplification in classification datasets
by: Tokas, Bhanu, et al.
Published: (2024)

Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation
by: Baade, Alan, et al.
Published: (2026)

Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning
by: Hsu, Kyle, et al.
Published: (2024)

RelDenClu: A Relative Density based Biclustering Method for identifying non-linear feature relations
by: Jain, Namita, et al.
Published: (2018)

Spatiotemporal Attention Learning Framework for Event-Driven Object Recognition
by: Xie, Tiantian, et al.
Published: (2025)

Sampling-guided exploration of active feature selection policies
by: Bernardino, Gabriel, et al.
Published: (2026)

The problems with using STNs to align CNN feature maps
by: Finnveden, Lukas, et al.
Published: (2020)

Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization
by: Pal, Shivam, et al.
Published: (2024)

Disentangling representations of retinal images with generative models
by: Müller, Sarah, et al.
Published: (2024)