Pith. sign in

REVIEW 8 cited by

Conditional Positional Encodings for Vision Transformers

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 2102.10882 v3 pith:L4HBYMSG submitted 2021-02-22 cs.CV cs.AIcs.LG

Xiangxiang Chu , Zhi Tian , Bo Zhang , Xinlong Wang , Chunhua Shen This is my paper
classification cs.CVcs.AIcs.LG
keywords positionalconditionalcpvtencodingencodingsinputvisionposition
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of input tokens, CPE is dynamically generated and conditioned on the local neighborhood of the input tokens. As a result, CPE can easily generalize to the input sequences that are longer than what the model has ever seen during training. Besides, CPE can keep the desired translation-invariance in the image classification task, resulting in improved performance. We implement CPE with a simple Position Encoding Generator (PEG) to get seamlessly incorporated into the current Transformer framework. Built on PEG, we present Conditional Position encoding Vision Transformer (CPVT). We demonstrate that CPVT has visually similar attention maps compared to those with learned positional encodings and delivers outperforming results. Our code is available at https://github.com/Meituan-AutoML/CPVT .

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. ALICE: Learning a General-Purpose Pathology Foundation Model from Vision, Vision-Language, and Slide-Level Experts

    cs.CV 2026-07 accept novelty 6.0 of 10

    Multi-stage agglomerative distillation consolidates eight vision, vision-language, and slide-level pathology teachers into one backbone that ranks first on average across 96 downstream tasks.

  2. ToFe: Lagged Token Freezing and Reusing for Efficient Vision Transformer Inference

    cs.CV 2025-07 conditional novelty 6.0 of 10

    ToFe freezes unimportant ViT tokens temporarily and reuses them later, achieving about 50% FLOPs reduction with less than 2% top-1 accuracy drop on ImageNet.

  3. Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learning

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Disrupting the spatial continuity of image tokens hurts source-domain accuracy far more than target-domain accuracy, and using such disruption during source training improves cross-domain few-shot classification.

  4. SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classification

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A spatial-aware MLP-Mixer with polar rotary position embedding and channel-shifting SAC blocks achieves state-of-the-art slide-level classification on CAMELYON-16, TCGA-LUNG, and TCGA-BRCA.

  5. Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysis

    eess.IV 2025-07 conditional novelty 5.0 of 10

    The paper introduces a shuffling-equivalence regularizer for MIL-based WSI analysis, claiming consistent gains over state-of-the-art methods.

  6. Compress image to patches for Vision Transformer

    cs.CV 2025-02 conditional novelty 5.0 of 10

    Using a frozen learned-compression encoder as the ViT patch embedder yields a 4x token reduction and 63% FLOP savings, with accuracy gains shown only on one small dataset.

  7. CoPE: A Lightweight Complex Positional Encoding

    cs.LG 2025-08 reject novelty 4.0 of 10

    CoPE, a complex positional encoding with imaginary-position and first-layer phase-aware attention, shows small GLUE gains but its no-decay proof and speed advantage are not fully supported.

  8. Vision Generalist Model: A Survey

    cs.CV 2025-06 conditional novelty 3.0 of 10

    A structured review of vision generalist models, classifying them into encoding-based and sequence-to-sequence frameworks and summarizing datasets, benchmarks, techniques, and open problems.

Pith tools