Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency

• URL: http://arxiv.org/abs/2506.10178v2
• Date: Mon, 06 Oct 2025 13:58:58 GMT
• Title: Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency
• Authors: Bill Psomas, Dionysis Christopoulos, Eirini Baltzi, Ioannis Kakogeorgiou, Tilemachos Aravanis, Nikos Komodakis, Konstantinos Karantzalos, Yannis Avrithis, Giorgos Tolias,
• Abstract summary: As fine-tuning becomes impractical at scale, probing is emerging as the preferred evaluation protocol.<n>This motivates the need for attentive probing, an alternative that uses attention to selectively aggregate patch-level features.<n>We present the first comprehensive study of existing methods, analyzing their design choices and benchmarking their performance.
• Score: 20.320991233039965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As fine-tuning becomes increasingly impractical at scale, probing is emerging as the preferred evaluation protocol. Yet, the standard linear probing fails to adequately reflect the potential of models whose pre-training optimizes representations of patch tokens rather than an explicit global representation. This motivates the need for attentive probing, an alternative that uses attention to selectively aggregate patch-level features. Despite its growing adoption, attentive probing remains under-explored, with existing methods suffering from excessive parameterization and poor computational efficiency. In this work, we revisit attentive probing through the lens of the accuracy vs. parameter efficiency trade-off. We present the first comprehensive study of existing methods, analyzing their design choices and benchmarking their performance. Building on this, we propose efficient probing (EP), a simple yet effective multi-query cross-attention mechanism that eliminates redundant projections and reduces the number of trainable parameters. Despite its simplicity, EP outperforms linear probing and prior attentive probing approaches across seven benchmarks, generalizes well to diverse pre-training paradigms, and delivers strong low-shot and layer-wise gains. Beyond evaluation, our analysis uncovers emerging properties of EP, such as complementary attention maps, which open new directions for leveraging probing beyond protocol design. Code available at https://github.com/billpsomas/efficient-probing.

Related papers

• Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization [11.10178274806454]
  We propose a form of weak supervision that improves the annotation efficiency and detection performance.<n>We re-annotated mainstream IML datasets with scribble labels and propose the first scribble-based IML dataset.<n>We employ self-supervised training with a structural consistency loss to encourage the model to produce consistent predictions.
  arXiv  Detail & Related papers  (2025-07-17T11:45:27Z)
• Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning [37.16998362490576]
  Representation Fine-tuning (ReFT) has attracted widespread attention for significantly improving parameter efficiency by editing representation space alone.<n>We propose Critical Representation Fine-Tuning (CRFT), a novel method that identifies and optimize these critical representations through information flow analysis.<n>Our method is validated across eight benchmarks for arithmetic and commonsense reasoning, using LLaMA and Mistral model families.
  arXiv  Detail & Related papers  (2025-07-14T09:11:33Z)
• Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion [52.315729095824906]
  MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD) is a novel framework that introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference.<n>It performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps.<n>Extensive experiments demonstrate PPAD's significant improvements.
  arXiv  Detail & Related papers  (2025-05-26T14:42:35Z)
• Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing [14.114970711442512]
  This paper introduces Attention Pruning, a fairness-aware simulated annealing approach to prune attention heads in large language models (LLMs)<n>Our experiments show that Attention Pruning achieves up to $40%$ reduction in gender bias and outperforms the state-of-the-art bias mitigation strategies.
  arXiv  Detail & Related papers  (2025-03-20T03:02:32Z)
• Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Models [85.51753014478315]
  We introduce AdaptPrune, a novel plug-and-play training-free pruning method.<n>It builds on conventional attention-based pruning by integrating spatial distance and token similarity with an adaptive NMS approach.<n>Our approach ensures a comprehensive evaluation of token importance and substantially refines the pruning decisions.
  arXiv  Detail & Related papers  (2025-03-11T03:58:17Z)
• PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity [9.092404060771306]
  Diffusion models have shown impressive results in generating high-quality conditional samples.<n>However, existing methods often require additional training or neural function evaluations (NFEs)<n>We propose a novel and efficient method, termed PLADIS, which boosts pre-trained models by leveraging sparse attention.
  arXiv  Detail & Related papers  (2025-03-10T07:23:19Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans [13.695885742446027]
  Self-attention can lead to over-concentration on a few tokens during training, resulting in suboptimal information flow.<n>We introduce a novel, fully parallelizable doubly-stochastic attention mechanism based on sliced optimal transport.<n>Our method enforces doublyity without iterative Sinkhorn normalization, significantly enhancing efficiency.
  arXiv  Detail & Related papers  (2025-02-11T21:20:48Z)
• Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More [26.226145789963443]
  Mask-Enhanced Autoregressive Prediction (MEAP) is a training paradigm that seamlessly integrates Masked Language Modeling (MLM) into Next-Token Prediction (NTP)<n>In intensive experiments, MEAP substantially outperforms NTP on key information retrieval and long-context reasoning tasks.<n>Our analysis indicates that MEAP's effectiveness arises from its ability to promote more distinguishable attention scores by concentrating on a reduced set of non-masked tokens.
  arXiv  Detail & Related papers  (2025-02-11T11:49:03Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Long-Sequence Recommendation Models Need Decoupled Embeddings [49.410906935283585]
  We identify and characterize a neglected deficiency in existing long-sequence recommendation models.<n>A single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes.<n>We propose the Decoupled Attention and Representation Embeddings (DARE) model, where two distinct embedding tables are learned separately to fully decouple attention and representation.
  arXiv  Detail & Related papers  (2024-10-03T15:45:15Z)
• A Universal Class of Sharpness-Aware Minimization Algorithms [57.29207151446387]
  We introduce a new class of sharpness measures, leading to new sharpness-aware objective functions. We prove that these measures are textitly expressive, allowing any function of the training loss Hessian matrix to be represented by appropriate hyper and determinants.
  arXiv  Detail & Related papers  (2024-06-06T01:52:09Z)
• Prototypical Contrastive Learning through Alignment and Uniformity for Recommendation [6.790779112538357]
  We present underlinePrototypical contrastive learning through underlineAlignment and underlineUniformity for recommendation. Specifically, we first propose prototypes as a latent space to ensure consistency across different augmentations from the origin graph. The absence of explicit negatives means that directly optimizing the consistency loss between instance and prototype could easily result in dimensional collapse issues.
  arXiv  Detail & Related papers  (2024-02-03T08:19:26Z)
• A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models [19.17722702457403]
  We show that state-of-the-artETL approaches exhibit strong performance only in narrowly-defined experimental setups. We propose a CLass-Adaptive linear Probe (CLAP) objective, whose balancing term is optimized via an adaptation of the general Augmented Lagrangian method.
  arXiv  Detail & Related papers  (2023-12-20T02:58:25Z)
• Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation [49.827306773992376]
  Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions. Our proposed method attains state-of-the-art performance in both classification and segmentation CTTA tasks.
  arXiv  Detail & Related papers  (2023-12-19T15:34:52Z)
• Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding [38.11411155621616]
  We study self-training as one of the predominant semi-supervised learning approaches. We present UPET, a novel Uncertainty-aware self-Training framework. We show that UPET achieves a substantial improvement in terms of performance and efficiency.
  arXiv  Detail & Related papers  (2023-10-19T02:18:29Z)
• Consensus-Adaptive RANSAC [104.87576373187426]
  We propose a new RANSAC framework that learns to explore the parameter space by considering the residuals seen so far via a novel attention layer. The attention mechanism operates on a batch of point-to-model residuals, and updates a per-point estimation state to take into account the consensus found through a lightweight one-step transformer.
  arXiv  Detail & Related papers  (2023-07-26T08:25:46Z)
• Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training [55.12082817901671]
  We propose a new self-supervised pre-training approach, named Masked and Permuted Vision Transformer (MaPeT)<n>MaPeT employs autoregressive and permuted predictions to capture intra-patch dependencies.<n>Our results demonstrate that MaPeT achieves competitive performance on ImageNet, compared to baselines and competitors under the same model setting.
  arXiv  Detail & Related papers  (2023-06-12T18:12:19Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
  Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples. We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment. We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
  arXiv  Detail & Related papers  (2022-03-23T06:24:31Z)
• Fast Rates for Contextual Linear Optimization [52.39202699484225]
  We show that a naive plug-in approach achieves regret convergence rates that are significantly faster than methods that directly optimize downstream decision performance. Our results are overall positive for practice: predictive models are easy and fast to train using existing tools, simple to interpret, and, as we show, lead to decisions that perform very well.
  arXiv  Detail & Related papers  (2020-11-05T18:43:59Z)
• Cross-Entropy Method Variants for Optimization [0.0]
  Cross-entropy (CE) method is a popular method for optimization due to its simplicity and effectiveness. Certain objective functions may be computationally expensive to evaluate, and the CE-method could potentially get stuck in local minima. We introduce novel variants of the CE-method to address these concerns.
  arXiv  Detail & Related papers  (2020-09-18T19:51:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.