Neural Radiance Fields (NeRF) have demonstrated remarkable potential for high-fidelity 3D scene reconstruction and rendering. However, achieving real-time performance remains a major challenge due to two critical bottlenecks: the high memory demand of multi-resolution hash encoding and the considerable computational cost of floating-point interpolation. To address these limitations, we propose Spiking-NeRF, a braininspired algorithm-hardware co-design framework. On the algorithm side, we introduce a spiking feature encoding scheme based on Integrate-and-Fire (IF) neurons, which transforms continuous voxel features into sparse spikes, reducing hash storage overhead by $\mathbf{7 5 \%}$. We further propose a global importance-based pruning strategy that compresses hash tables by $\mathbf{7 1. 3 \%}$ by removing lowaccessed entries. To reduce interpolation complexity, we design a hard-threshold weight discretization method that eliminates floating-point operations in favor of bitwise logic. On the hardware side, we accelerate critical stages of the NeRF pipeline by integrating a spike-skipping mechanism that dynamically bypasses hash entries, reducing memory traffic by 32.46%. We also co-optimize on-chip storage by leveraging access locality patterns across different resolution levels of the hash structure. Experimental results demonstrate that Spiking-NeRF achieves real-time rendering performance while maintaining high visual fidelity. Compared to edge GPUs, our design improves throughput by $111.2 \times$ and reduces power consumption by $41.67 \times$. Against SOTA NeRF accelerators, Spiking-NeRF achieves up to $2.48 \times$ higher throughput and $5.45 \times$ lower energy usage, underscoring the potential of spike-based computing for next-generation lowpower neural graphics systems.

Structural re-parameterization is a raising field, which aims at improving the performance of convolutional neural networks (CNNs) through training an over-parameterization model and transferring it into a compact inference model. However, the performance improvements of prior structural re-parameterization works often come at the cost of heavy extra training resources, which increases carbon emissions and limits the potential applications on large-scale industrial tasks. To this end, first, we conduct experiments with a series of blocks composed of multiple identical branches to investigate the mechanism behind the structural re-parameterization, and then provide an interpretation. Moreover, motivated by the studies of effective receptive fields in the biological visual systems and neural networks, we propose a novel compact block named circular mask block (CMB). Given a neural network, we replace the regular convolutional layer with CMB to construct a training architecture, which can be trained to gain an accuracy boost with No extra training parameters and limited extra training FLOPs. After training, the training architecture can be transformed into the original architecture for inference. Extensive experiments are performed on CIFAR-10 and ImageNet to evaluate the effectiveness of our method. For example, we improve 0.85% top-1 accuracy of ResNet-50 on ImageNet without extra training parameters and only 11.32M extra training FLOPs, which saves 434x training FLOPs compared with prior works.

Network pruning is an effective and widely-used model compression technique. Pattern pruning is a new sparsity dimension pruning approach whose compression ability has been proven in some prior works. However, a detailed study on "pattern" and pattern pruning is still lacking. In this paper, we analyze the mechanism behind pattern pruning. Our analysis reveals that the effectiveness of pattern pruning should be attributed to finding the less important weights even before training. Then, motivated by the fact that the retinal ganglion cells in the biological visual system have approximately concentric receptive fields, we further investigate and propose the Circle Importance Hypothesis to guide the design of efficient patterns. We also design two series of special efficient patterns - circle patterns and semicircle patterns. Moreover, inspired by the neural architecture search technique, we propose a novel one-shot gradient-based pattern pruning algorithm. Besides, we also expand depthwise convolutions with our circle patterns, which improves the accuracy of networks with little extra memory cost. Extensive experiments are performed to validate our hypotheses and the effectiveness of the proposed methods. For example, we reduce the 44.0% FLOPS of ResNet-56 while improving its accuracy to 94.38% on CIFAR-10. And we reduce the 41.0% FLOPS of ResNet-18 with only a 1.11% accuracy drop on ImageNet.

Pruning can remove the redundant parameters and structures of Deep Neural Networks (DNNs) to reduce inference time and memory overhead. As one of the important components of DNN, feature maps (FMs) have been widely used in network pruning. However, previous approaches do not fully investigate the discriminative features in FMs, and also do not explicitly utilize all the features associated with each layer in the pruning procedure. In this paper, we explore the discriminative feature of FMs and explicitly investigate the two-adjacent-layer features of each layer to propose a three-phase hierarchical pruning framework, dubbed as FCHP. Firstly, we decompose each FM into several components to extract the discriminative feature. After that, since pruning each layer is related to the FMs of adjacent layers, we explicitly calculate the feature correlation of discriminative features of two adjacent layers, and then use the feature correlation to cluster FMs into several hierarchies to guide subsequent pruning. Finally, we compute the content of discriminative features, and remove channels corresponding to FMs with fewer discriminative features in each hierarchy, respectively. In the experiment, we prune DNNs with the multiple types of architecture on different benchmarks, and the results have achieved the state-of-the-arts in terms of compressed parameters and FLOPs drop. For example, as for ResNet-56 on CIFAR-10, FCHP respectively obtains 50% of parameters and FLOPs reduction with negligible accuracy loss. Besides, as for ResNet-50 on ImageNet, FCHP reduces 40.5% of parameters and 44.1% of FLOPs with 0.43% of Top-1 accuracy drop.

Pruning can remove redundant parameters and structures of Deep Neural Networks (DNNs) to reduce inference time and memory overhead. As an important component of neural networks, the feature map (FM) has stated to be adopted for network pruning. However, the majority of FM-based pruning methods do not fully investigate effective knowledge in the FM for pruning. In addition, it is challenging to design a robust pruning criterion with a small number of images and achieve parallel pruning due to the variability of FMs. In this paper, we propose Adaptive Knowledge Extraction for Channel Pruning (AKECP), which can compress the network fast and efficiently. In AKECP, we first investigate the characteristics of FMs and extract effective knowledge with an adaptive scheme. Secondly, we formulate the effective knowledge of FMs to measure the importance of corresponding network channels. Thirdly, thanks to the effective knowledge extraction, AKECP can efficiently and simultaneously prune all the layers with extremely few or even one image. Experimental results show that our method can compress various networks on different datasets without introducing additional constraints, and it has advanced the state-of-the-arts. Notably, for ResNet-110 on CIFAR-10, AKECP achieves 59.9% of parameters and 59.8% of FLOPs reduction with negligible accuracy loss. For ResNet-50 on ImageNet, AKECP saves 40.5% of memory footprint and reduces 44.1% of FLOPs with only 0.32% of Top-1 accuracy drop.