Papers for

security camera manufacturers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Spiking neural network design slashes parameters for event vision

RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision

Abstract: Spiking-Mamba hybrids reach strong accuracy on event-based vision, but existing designs often require tens of millions of parameters. Much of that cost comes from how the spiking front-end is connected to the state-space backbone rather than from the hybrid architecture itself. In a representative model, a single resolution-dependent projection accounts for 33.55M of 36.25M parameters. To that end, we introduce RIPE-MambaSpike (Resolution-Independent, Parameter-Efficient), which replaces that projection with a hierarchical multi-resolution bridge of fixed channel width. Its deployed footprint is 0.870M parameters, constant at fixed time steps and widths across a 43x range of input areas. Reparameterized spiking stages, temporal decoupled modulation, and a dynamic convex-hull-bounded dual-stream membrane-potential attention preserve accuracy under this compact design. Result-wise, RIPE-MambaSpike is pareto-optimal on CIFAR10-DVS, N-Caltech101, and DailyDVS-200. Notably, on the 200-class DailyDVS-200, a scaled 8.04M configuration achieves 45.7% top-1 accuracy, the best reported spiking result on that benchmark, and outperforms prior spiking methods with 3.0-15.1x fewer parameters than dense ANNs. Overall, our findings demonstrate that competitive event-based recognition does not require resolution-dependent parameter growth. Code is available at https://github.com/MuhiminOsim/RIPE-MambaSpike.

Sat 26 SeptComputer Vision and Pattern RecognitionNeural and Evolutionary Computing

The gist

Event-based vision systems let computers see and react like human eyes by processing changes rather than full images. But using spiking neural networks to do this usually needs huge numbers of parameters, making them hard to run efficiently. The authors made a new design called RIPE-MambaSpike that cuts this parameter count drastically without losing accuracy by changing how the system handles different image resolutions. Their method works well on several benchmark datasets and sets a new accuracy record on a challenging dataset using fewer resources than previous methods.

Open → 2609.32537v1

Efficient quantization aware training improves vision language models on edge

Efficient Quantization-Aware Distillation with Cross-Modal Alignment for Edge Vision-Language Models

Abstract: Large-scale vision-language models (VLM) such as CLIP enable strong open-vocabulary reasoning, yet deploying these capabilities on resource-constrained edge devices remains challenging. EdgeVL addresses this problem by distilling CLIP representations into lightweight multi-modal encoders and applying quantization-aware training (QAT) for efficient Open-Vocabulary Classification (OVC) on edge hardware. However, its two-stage optimization applies different objectives for distillation and QAT, and contrastive learning is performed within the quantized student space, which can result in inconsistent optimization and reduced training efficiency. Moreover, identical supervision across RGB and non-RGB modalities may lead to modality imbalance. We propose a unified framework for quantized semantic distillation tailored to edge deployment. By jointly optimizing distillation and quantization within a unified teacher-anchored framework, our method ensures consistent training under quantization, suppressing hard negatives and enlarging decision margins. Additionally, we design a lightweight cross-attention adapter that enhances non-RGB representations through RGB-guided semantic transfer, narrowing the modality gap. Extensive experiments demonstrate consistent improvements on non-RGB modalities while maintaining deployment efficiency.

Tue 15 SeptComputer Vision and Pattern Recognition

The gist

Running large vision-language AI models on small devices like phones is hard because these models use a lot of memory and computing power. The authors propose a new method that trains smaller versions of these models to work better within limited hardware by combining two training steps into one, making the training more consistent. They also improved how the model handles different types of image inputs by letting one type help guide another. Their approach makes running these models on edge devices more accurate and efficient.

Open → 2609.16689v1