DeepMine-Mamba addresses information dilution in Mamba-based state space models for document image binarization. The authors show that state-space propagation amplifies both foreground and background, reducing contrast, and introduce an Anti‑Dilution Gate that uses propagation‑induced differences and a learned stroke prior to preserve stroke details. On DIBCO/H‑DIBCO benchmarks without external data, the method matches transformer and gated‑convolution baselines and improves all four evaluation metrics.
arXiv:2607. 18625v1 Announce Type: cross Abstract: Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones.
arXiv:2609.27149v1 Announce Type: new Abstract: Remote sensing change detection requires both global reasoning across bitemporal images and precise localization of changed regions. However, dense att...
The paper revisits the use of contrastive loss for post‑training CLIP models, showing that the reported catastrophic forgetting is mainly due to an overly large temperature parameter in the InfoNCE objective. By setting a smaller temperature, contrastive post‑training can actually improve CLIP. The authors introduce ComCLIP, a lightweight single‑epoch recipe that freezes the text encoder, trains the vision encoder with a properly tempered contrastive loss, an MSE anchoring loss, and a relational distillation loss, achieving comparable zero‑shot classification to CLIP‑Refine while significantly enhancing visual feature transferability and maintaining downstream compatibility with LLaVA.
Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience. While modern vision models achieve strong performance in image recognition, their correspondence with the hierarchical organization of the human visual cortex remains an open question.
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:2606. 04772v1 Announce Type: cross Abstract: Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience.
arXiv:2609.24049v1 Announce Type: new Abstract: Accurate retinal vessel segmentation is important for computer-aided ophthalmic analysis, yet thin vessels, low contrast, and severe foreground-backgro...
arXiv:2412.10338v4 Announce Type: replace Abstract: Deep state-space models (SSMs), like recent Mamba architectures, are emerging as a promising alternative to CNN and Transformer networks. Existing...
The paper proposes a multi‑branch conditional GAN that fuses visible, near‑infrared, and structural features for multispectral document binarization. By applying spatial‑ and channel‑wise softmax gating at encoder depth 3 and guiding the fusion with edge maps from selected VIS‑NIR band pairs, the authors evaluate nine configurations and find that the F3 + NIR edge‑guided model achieves the best performance, improving F1, p‑FM, and IoU over a fixed‑average baseline with statistically significant gains. The study demonstrates that targeted cross‑spectral structural guidance can effectively regulate intermediate fusion and enhance foreground‑overlap accuracy while preserving all four spectral bands.
The paper introduces IsoMamba, a Vision Mamba variant that addresses state contention in underwater image enhancement by organizing recurrent states according to token compatibility. It employs a cluster–route–isolate paradigm to route update‑compatible tokens into independent state streams and adds a dynamic channel‑wise reweighting objective to handle wavelength‑dependent reconstruction challenges. Experiments show IsoMamba outperforms existing methods on multiple underwater enhancement benchmarks while producing cleaner hidden state responses.
arXiv:2609.23061v1 Announce Type: new Abstract: Small-object detection in UAV imagery is challenged by weak visual evidence, ambiguous boundaries, dense object distributions, and complex backgrounds....
arXiv:2607. 01876v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal understanding, yet their enormous parameter scale and cross-modal computation incur substantial memory and latency overhead, severely limiting real-world deployment on resource-constrained devices.