Pith. sign in

REVIEW 6 cited by

Vision Transformer Pruning

Not yet reviewed by Pith; the record is open.

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 2104.08500 v4 pith:ZWMXTV5R submitted 2021-04-17 cs.CV

classification cs.CV
keywords pruningtransformervisiondimensionsproposedsparsityaccordinglyaccuracy
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Vision transformer has achieved competitive performance on a variety of computer vision applications. However, their storage, run-time memory, and computational demands are hindering the deployment to mobile devices. Here we present a vision transformer pruning approach, which identifies the impacts of dimensions in each layer of transformer and then executes pruning accordingly. By encouraging dimension-wise sparsity in the transformer, important dimensions automatically emerge. A great number of dimensions with small importance scores can be discarded to achieve a high pruning ratio without significantly compromising accuracy. The pipeline for vision transformer pruning is as follows: 1) training with sparsity regularization; 2) pruning dimensions of linear projections; 3) fine-tuning. The reduced parameters and FLOPs ratios of the proposed algorithm are well evaluated and analyzed on ImageNet dataset to demonstrate the effectiveness of our proposed method.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. FastTPS: An Optimized Method for LLM Token Phase for AI accelerators

    cs.LG 2026-07 conditional novelty 6.0 of 10

    FastTPS accelerates LLM token-phase inference via reloading-free static KV-cache management, tiled fused RoPE attention, and interlaced-weight MLP fusion, yielding up to 6× speedup at 93% bandwidth on AMD NPUs.

  2. Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Heterogeneity-aware depth pruning of attention and activation layers, guided by a polynomial model-accuracy predictor, delivers up to 1.58× speedup on DeiT-B and 5.19× when combined with width pruning.

  3. L-CLIPScore: a Lightweight Embedding-based Captioning Metric for Evaluating and Training

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A distilled 99M-parameter CLIP gives L-CLIPScore, a lightweight caption metric that matches CLIPScore on human correlation and best improves captioning models when mixed with CIDEr.

  4. Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework

    cs.LG 2024-11 conditional novelty 6.0 of 10

    SNOWS prunes vision networks in one shot by optimizing a K-step nonlinear reconstruction objective with Hessian-free Newton steps, improving accuracy over layer-wise least-squares methods.

  5. QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models

    cs.CV 2025-07 conditional novelty 5.0 of 10

    QuarterMap prunes spatial activations before VMamba's four-directional scan and upsamples after, yielding up to 1.11x throughput with under 1% accuracy loss on ImageNet classification.

  6. V"Mean"ba: Visual State Space Models only need 1 hidden dimension

    cs.CV 2024-12 conditional novelty 4.0 of 10

    VMeanba speeds up VMamba's selective scan by averaging its internal channel dimension down to 1, achieving up to 1.12x end-to-end speedup with under 3% accuracy loss on ImageNet and ADE20k.

Pith tools