Pith. sign in

REVIEW 12 cited by

Speeding up Convolutional Neural Networks with Low Rank Expansions

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1405.3866 v1 pith:FL77XHB7 submitted 2014-05-15 cs.CV

Max Jaderberg , Andrea Vedaldi , Andrew Zisserman This is my paper · ORCID
classification cs.CV
keywords convolutionalnetworksspeedingspeedupaccuracylayersneuralrank
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The focus of this paper is speeding up the evaluation of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learning tasks, these networks are computationally demanding, limiting their deployability. Convolutional layers generally consume the bulk of the processing time, and so in this work we present two simple schemes for drastically speeding up these layers. This is achieved by exploiting cross-channel or filter redundancy to construct a low rank basis of filters that are rank-1 in the spatial domain. Our methods are architecture agnostic, and can be easily applied to existing CPU and GPU convolutional frameworks for tuneable speedup performance. We demonstrate this with a real world network designed for scene text character recognition, showing a possible 2.5x speedup with no loss in accuracy, and 4.5x speedup with less than 1% drop in accuracy, still achieving state-of-the-art on standard benchmarks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization

    cs.CV 2024-08 unverdicted novelty 7.0 of 10

    CoRa reclaims quantization residuals in pre-trained ConvNets by searching low-rank adapter architectures instead of weights, matching SOTA accuracy on ImageNet in 3-4 bit settings with under 250 iterations on 1600 images.

  2. Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion

    cs.GR 2025-09 conditional novelty 6.0 of 10

    A diffusion model over per-person UNet weights generates new dynamic human avatars that render pose-dependent 3D Gaussians in real time.

  3. Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives

    cs.LG 2025-02 conditional novelty 6.0 of 10

    Dobi-SVD compresses LLMs via differentiable SVD rank selection, IPCA-based weight reconstruction, and quantized storage remapping, reporting competitive perplexity at 40% parameters.

  4. Hardware-Efficient Photonic Tensor Core: Accelerating Deep Neural Networks with Structured Compression

    cs.AR 2025-02 conditional novelty 6.0 of 10

    A block-circulant photonic tensor core runs structure-compressed image classifiers within about 1.4 to 3.7 percentage points of full-precision digital models while reducing trainable parameters by up to 74.91%.

  5. ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models

    cs.CL 2023-12 unverdicted novelty 6.0 of 10

    ASVD compresses LLMs by 10-30% and KV caches by 50% via activation-aware SVD that absorbs outliers into transformed weights and calibrates per-layer sensitivity.

  6. EinSort: Sorting is All We Need for Tensorizing LLM

    cs.LG 2026-06 unverdicted novelty 5.0 of 10

    Sorting tensor indices enables an adaptive tensorization method that discovers low-rank structure in LLM weights and KV caches, yielding better reconstruction quality than baselines.

  7. On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Compression methods can be seen as information projections, and iterative soft rank reduction, not the projection choice, dominates performance after fine-tuning, with a convergence proof for iterative singular value ...

  8. Advanced deep architecture pruning using single filter performance

    cs.LG 2025-01 reject novelty 5.0 of 10

    AFCC pruning keeps only filter-to-filter connections whose filters share cluster labels and reports preserved accuracy on CIFAR-100, but its masks are computed on the test set.

  9. SMM-Conv: Scalar Matrix Multiplication with Zero Packing for Accelerated Convolution

    cs.CV 2024-11 conditional novelty 5.0 of 10

    SMM-Conv computes convolutions by accumulating kernel-scaled shifted sub-matrices into the output, reusing a single buffer, and reports speedups over im2col+GEMM and MEC on CPU.

  10. A Discrepancy-Based Perspective on Dataset Condensation

    cs.LG 2025-09 conditional novelty 4.0 of 10

    Dataset condensation is reframed as minimizing distribution discrepancies, and existing methods are sorted into a taxonomy; no new algorithm or experiments are provided.

  11. Structure-Aware Automatic Channel Pruning by Searching with Graph Embedding

    cs.AI 2025-06 reject novelty 4.0 of 10

    A graph-embedding search over discretized pruning rates, guided by contrastive learning, claims high compression on CIFAR-10 but lacks key validation.

  12. Recent Advances and Trends in Learning-based 3D Representations

    cs.CV 2026-06 unverdicted novelty 3.0 of 10

    A survey of 3D representation families that highlights the shift from discrete explicit formats to continuous implicit neural and primitive-based ones.

Pith tools