Pith. sign in

REVIEW 8 cited by

Patches Are All You Need?

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 2201.09792 v1 pith:YZW2HQRQ submitted 2022-01-24 cs.CV cs.AIcs.LG

classification cs.CVcs.AIcs.LG
keywords convmixerinputpatchessomevisionarchitecturehoweverimage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Although convolutional networks have been the dominant architecture for vision tasks for many years, recent experiments have shown that Transformer-based models, most notably the Vision Transformer (ViT), may exceed their performance in some settings. However, due to the quadratic runtime of the self-attention layers in Transformers, ViTs require the use of patch embeddings, which group together small regions of the image into single input features, in order to be applied to larger image sizes. This raises a question: Is the performance of ViTs due to the inherently-more-powerful Transformer architecture, or is it at least partly due to using patches as the input representation? In this paper, we present some evidence for the latter: specifically, we propose the ConvMixer, an extremely simple model that is similar in spirit to the ViT and the even-more-basic MLP-Mixer in that it operates directly on patches as input, separates the mixing of spatial and channel dimensions, and maintains equal size and resolution throughout the network. In contrast, however, the ConvMixer uses only standard convolutions to achieve the mixing steps. Despite its simplicity, we show that the ConvMixer outperforms the ViT, MLP-Mixer, and some of their variants for similar parameter counts and data set sizes, in addition to outperforming classical vision models such as the ResNet. Our code is available at https://github.com/locuslab/convmixer.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Gene Ontology-Guided Hierarchical Spatial Gene Expression Prediction from Histopathology Images

    cs.AI 2026-08 conditional novelty 6.0 of 10

    MSGR's Gene Ontology-guided hierarchical decoder improves spatial gene expression prediction from histology images, with the biological structure adding a +0.027 gain over an equivalent random hierarchy.

  2. UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A heterogeneous pyramidal vision encoder plus two-stage dense-then-generative pre-training yields faster, stronger on-device LVLM vision encoding than FastVLM.

  3. SWIFT: Spatio-temporal Wavelet Integrated Forecasting Framework for Workload Traces

    cs.DC 2026-05 conditional novelty 6.0 of 10

    SWIFT forecasts cloud workloads at SOTA accuracy with linear complexity by combining learnable cascaded wavelet convolutions and sequential inter/intra-variable mixing.

  4. Learning High-Level Decision Making with an Interaction-Aware Attention-Based Network in Autonomous Driving

    cs.RO 2026-06 conditional novelty 5.0 of 10

    An attention architecture that bottlenecks traffic agents into fixed latent queries plus a finer discrete action set yields higher simulated speeds and lower early-termination rates than DeepSet and Ego-attention on t...

  5. Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms

    cs.CV 2025-08 conditional novelty 5.0 of 10

    LOLViT, a GhostNet-based lightweight backbone using adaptive window attention, reports CNN-like CPU speed with MobileViT-level accuracy.

  6. LaVi: Efficient Large Vision-Language Models via Internal Feature Modulation

    cs.CV 2025-06 conditional novelty 5.0 of 10

    LaVi encodes visual context into LayerNorm affine parameters, bypassing visual token concatenation, and reports LLaVA-comparable accuracy at a 94% FLOP reduction.

  7. Accurate and efficient zero-shot 6D pose estimation with frozen foundation models

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A training-free 6D pose estimator using sparse-to-dense matching of frozen foundation model features achieves new state-of-the-art results on BOP with large speedups.

  8. Modernizing CNN-based Weather Forecast Model towards Higher Computational Efficiency

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A 7-million-parameter convolutional weather model trains in 12 hours on one GPU and is reported to match or beat much larger AI and numerical weather models in medium-range forecasts.

Pith tools