Pith. sign in

REVIEW 17 cited by

Exploring Visual Prompts for Adapting Large-Scale Models

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 2203.17274 v2 pith:3A3AO5IF submitted 2022-03-31 cs.CV

Exploring Visual Prompts for Adapting Large-Scale Models

classification cs.CV
keywords visualpromptingmodelsadaptinglarge-scaleperformanceperturbationprompt
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We investigate the efficacy of visual prompting to adapt large-scale models in vision. Following the recent approach from prompt tuning and adversarial reprogramming, we learn a single image perturbation such that a frozen model prompted with this perturbation performs a new task. Through comprehensive experiments, we demonstrate that visual prompting is particularly effective for CLIP and robust to distribution shift, achieving performance competitive with standard linear probes. We further analyze properties of the downstream dataset, prompt design, and output transformation in regard to adaptation performance. The surprising effectiveness of visual prompting provides a new perspective on adapting pre-trained models in vision. Code is available at http://hjbahng.github.io/visual_prompting .

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 17 Pith papers

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

  1. One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models

    cs.CV 2026-06 unverdicted novelty 7.0

    Introduces MultiDepth-3k benchmark revealing diverse layer preferences across depth models on ambiguous scenes, with Laplacian Visual Prompting altering outputs for some frozen models and best pair reaching 75.5% ML-SRA.

  2. Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training

    cs.LG 2026-06 unverdicted novelty 7.0

    ART optimizes visual pixel inputs to frozen MLLMs to achieve LoRA-competitive accuracy on math and structured tool-use benchmarks without modifying computational graphs.

  3. BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning

    cs.CR 2026-05 unverdicted novelty 7.0

    BadBone backdoors backbone models with bi-level optimization to make prompt learning on downstream tasks vulnerable while preserving model utility.

  4. Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection

    cs.CV 2026-05 unverdicted novelty 7.0

    Thermal-Det is the first LLM-supervised open-vocabulary thermal object detector, created via synthetic data conversion from GroundingCap-1M and RGB-to-thermal distillation, yielding 2-4% AP gains on benchmarks.

  5. Visual prompt engineering for video models

    cs.CV 2026-07 conditional novelty 6.0

    Automatically converting task images to photorealistic variants (visual prompt engineering) improves video-model reasoning performance, often beating text prompt engineering and test-time scaling.

  6. Language-Instructed Vision Embeddings for Controllable and Generalizable Perception

    cs.CV 2026-06 unverdicted novelty 6.0

    LIVE uses language to generate task-centric vision embeddings at inference, reducing hallucinations by 34 points on MMVP, outperforming larger VLMs on VQA, and generalizing to unseen tasks.

  7. Latent Diffusion Pretraining for Crystal Property Prediction

    cs.LG 2026-05 unverdicted novelty 6.0

    CrysLDNet combines VAE and latent diffusion pretraining on unlabeled crystals to improve graph encoder performance on property prediction by about 4-5% on JARVIS and MP datasets.

  8. TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 6.0

    TAME uses a Mixture-of-Experts prompt bank with input-dependent routing and three unsupervised objectives to adaptively defend CLIP against adversarial attacks at inference time, achieving at least 49.1% robustness ga...

  9. Plug-and-play Class-aware Knowledge Injection for Prompt Learning with Visual-Language Model

    cs.CV 2026-05 unverdicted novelty 6.0

    CAKI generates class-specific prompts from few-shot samples of the same class, stores them in a knowledge bank, and uses query-key matching to inject relevant class knowledge into test instance predictions for improve...

  10. Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models

    cs.CV 2026-04 unverdicted novelty 6.0

    Three frameworks adapt foundation models for generalized category discovery under domain shifts via disentanglement and prompt tuning, showing gains on synthetic and real multi-domain data.

  11. Visual prompting reimagined: The power of the Activation Prompts

    cs.CV 2026-04 unverdicted novelty 6.0

    Activation prompts on intermediate layers outperform input-level visual prompting and parameter-efficient fine-tuning in accuracy and efficiency across 29 datasets.

  12. Robust Adaptation of Foundation Models with Black-Box Visual Prompting

    cs.CV 2024-07 unverdicted novelty 6.0

    BlackVIP adapts foundation models via a Coordinator for input-dependent visual prompts and SPSA-GC for gradient estimation, enabling robust transfer on 19 datasets with low memory use and a link to randomized smoothin...

  13. Subgraph-level Universal Prompt Tuning

    cs.LG 2024-02 unverdicted novelty 6.0

    SUPT assigns prompt features at the subgraph level to enable universal prompt tuning for any GNN pre-training strategy and outperforms fine-tuning in 42 of 45 full-shot and 41 of 45 few-shot graph experiments with ave...

  14. Efficient Prompt Learning for Traffic Forecasting

    cs.LG 2026-05 unverdicted novelty 5.0

    SimpleST is a model-agnostic prompt tuning framework that lets pre-trained spatio-temporal GNNs adapt to distribution shifts in traffic data while keeping all original model weights fixed.

  15. MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation

    cs.CV 2026-02 conditional novelty 5.0

    MMLoP compresses deep multi-modal prompts into a rank-1 shared subspace, reaching a 79.70% base-to-novel harmonic mean with 11.5K trainable parameters.

  16. Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weighting

    cs.CV 2025-10 conditional novelty 5.0

    CAW adds a confidence-weighted KL loss and feature-alignment regularization to CLIP adversarial fine-tuning, raising average AutoAttack robust accuracy from 31.6% to 33.5% on 15 datasets.

  17. A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

    cs.AI 2024-02 unverdicted novelty 3.0

    A systematic survey categorizes prompt engineering methods for LLMs and VLMs by application area, summarizing methodologies, applications, models, datasets, strengths, and limitations for each technique along with a t...