arXiv:2607. 06982v1 Announce Type: cross Abstract: Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks.
Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks. However, the prohibitive computational cost of CNNs hinders the deployment of CNNs onto resource-constrained embedded devices.
arXiv:2609.22807v1 Announce Type: new Abstract: Implicit Neural Representation (INR) leverages neural networks to represent discrete signals such as images as continuous ones, where the network weigh...
The paper introduces S$^3$F-Net, a dual‑branch network that fuses spatial and spectral representations for medical image classification. It combines a deep spatial CNN with a shallow spectral encoder, SpectraNet, which uses a learnable SpectralFilter layer to process the full Fourier spectrum efficiently. Evaluated on four medical imaging datasets, S$^3$F-Net consistently outperforms spatial‑only baselines, achieving state‑of‑the‑art accuracy on BRISC2025 and surpassing deeper models on the Chest X‑Ray Pneumonia dataset.
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:2106. 06998v5 Announce Type: replace Abstract: Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation.
Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.
arXiv:2607.01630v2 Announce Type: replace Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our...
arXiv:2606. 07633v1 Announce Type: cross Abstract: Accurate classification of nuclei subtypes in histopathology images is critical for downstream tasks including tumor grading, immune infiltrate quantification, and prognosis prediction.
arXiv:2606. 03825v1 Announce Type: new Abstract: Transformers have become the dominant architecture for large language models, largely due to the scalability and flexibility of attention, feed-forward layers, residual connections, and normalization.
ProgResViT is an input‑adaptive Vision Transformer that processes images progressively across multiple rounds, starting with a low‑resolution image and a narrow subnetwork and refining the prediction with higher resolution and a wider subnetwork if needed. The method introduces Progress‑Conditioned Soft Gating (PSG) to share a single backbone across rounds while conditioning token fusion and layer outputs on the current round, block, and input resolution. Experiments on DeiT show improved accuracy‑compute trade‑offs compared to adaptive‑width, adaptive‑depth, and dynamic‑token baselines, and the design also benefits self‑supervised DINO representations and downstream semantic segmentation.
arXiv:2606. 09928v1 Announce Type: cross Abstract: The Forward-Forward (FF) algorithm offers a biologically inspired alternative to backpropagation by replacing gradient-based credit assignment with local, forward-only objectives.