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: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.
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.
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: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: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...
arXiv:2509. 09151v2 Announce Type: replace-cross Abstract: Research in video understanding has advanced rapidly, driven by increasingly diverse datasets and more powerful model architectures.
arXiv:2606. 15956v1 Announce Type: cross Abstract: Progress in AI has largely been driven by methods that assume less.
arXiv:2606. 09658v1 Announce Type: cross Abstract: Muon has recently emerged as a state-of-the-art optimizer for pretraining Large Language Models (LLMs) and vision classifiers.
Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning the necessity of SSMs for vision.
arXiv:2607. 16295v1 Announce Type: cross Abstract: Mechanistic interpretability has made significant strides in understanding neural network representations, with sparse dictionary learning (SDL) methods, most prominently sparse autoencoders, as a central paradigm.
arXiv:2603. 25157v3 Announce Type: replace-cross Abstract: Recent vision backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress on image recognition.