arXiv Computer Vision August 25, 2026 By Soudeep Ghoshal, Himanshu Buckchash

GradAttn: Replacing Fixed Residual Connections with Task-Modulated Attention Pathways

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jun 16

A biological vision inspired framework for machine perception of abutting grating illusory contours

arXiv:2508. 17254v2 Announce Type: replace-cross Abstract: Higher levels of machine intelligence demand alignment with human perception and cognition.

By Xiao Zhang, Kai-Fu Yang, Xian-Shi Zhang, Hong-Zhi You, Hong-Mei Yan, Yong-Jie Li

benchmarks safety

Hugging Face Trending Papers

Jun 22

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions

Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their performance remain incomplete. From a statistical viewpoint, a natural question is: can DNNs attain feature-learning and prediction consistency comparable to that of classical models?

computer-vision benchmarks

arXiv Machine Learning

Aug 4

LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks

arXiv:2511. 12723v2 Announce Type: replace Abstract: Deep neural networks typically rely on the representation produced by their final hidden layer to make predictions, implicitly assuming that this single vector fully captures the semantics encoded across all preceding transformations.

By Gennaro Vessio

rag computer-vision safety

arXiv Machine Learning

Jun 30

Meta-learning as a principle for human-like visual representations

arXiv:2606. 28399v1 Announce Type: cross Abstract: The structure of human visual representations underpins our capacity for adaptive behaviour.

By Can Demircan, Marcel Binz, Alireza Modirshanechi, Eric Schulz

safety

arXiv AI

Jul 7

Hyperparameter Transfer in Graph Neural Networks

arXiv:2607. 05017v1 Announce Type: cross Abstract: The performance of deep learning models crucially depends on the settings of hyperparameters like learning rate, initialization scale, and weight decay.

By Gage DeZoort, Boris Hanin

arXiv AI

Jun 26

Semantic Generative Tuning for Unified Multimodal Models

arXiv:2605. 18714v2 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.

By Songsong Yu, Yuxin Chen, Ying Shan, Yanwei Li

computer-vision multimodal benchmarks

One email a morning, machine-written

Related stories

A biological vision inspired framework for machine perception of abutting grating illusory contours

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions

LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks

Meta-learning as a principle for human-like visual representations

Hyperparameter Transfer in Graph Neural Networks

Semantic Generative Tuning for Unified Multimodal Models