arXiv Computer Vision
Exploring perceptual straightness in learned visual representations
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 16
Extremely coarse learning objectives induce human-aligned representations in AI vision models
arXiv:2605.05556v2 Announce Type: replace Abstract: Artificial neural networks trained on visual tasks develop internal representations resembling those of the primate visual system, a discovery that...
arXiv Machine Learning
Jul 8
Drift Happens: An Empirical Study of Neural Architecture Robustness to Temporal Distribution Shift
arXiv:2607. 05908v1 Announce Type: new Abstract: Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine learning systems.
arXiv Machine Learning
Oct 9
HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification
The paper introduces HAND, a biologically-inspired activation function that incorporates homeostasis, accelerating nonlinearity, and divisive normalization to act as an inductive bias in deep neural networks. Experiments on image classification show that using HAND allows a ConvNeXt-tiny model to reach ImageNet1k accuracy in 25 epochs versus 200 epochs for the baseline, and yields larger accuracy gains on long-tailed and reduced-data settings. The authors report that HAND does not degrade generalisation on common corruptions and can improve the model’s ability to reject unknown classes, with benefits observed across multiple CNN architectures and datasets.
arXiv Computer Vision
Aug 25
GradAttn: Replacing Fixed Residual Connections with Task-Modulated Attention Pathways
GradAttn replaces fixed residual connections in deep ConvNets with attention‑controlled gradient pathways, allowing the network to dynamically weight shallow texture features and deep semantic representations. The method extracts multi‑scale CNN features at different depths and regulates them through self‑attention, leading to improved performance over ResNet‑18 on five of eight evaluated datasets, including a +11.07% accuracy gain on FashionMNIST. Analysis of gradient flow shows that controlled instabilities introduced by attention can coincide with better generalization, while positional encoding proves to be dataset‑dependent.
arXiv AI
Jun 9
A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers
arXiv:2606. 07593v1 Announce Type: cross Abstract: The widespread use of image classification models in high-risk, real-world situations necessitates making these models robust to slight disturbances or perturbations, such as blurring or sharpening, in the input images.
arXiv Computer Vision
Oct 1
Image Classifiers are Efficient Self-Supervised Video Representation Learners
arXiv:2609.40347v1 Announce Type: new Abstract: We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of r...