CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification

• URL: http://arxiv.org/abs/2403.09281v3
• Date: Tue, 25 Mar 2025 16:47:11 GMT
• Title: CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
• Abstract summary: We propose CLIP-EBC, the first fully CLIP-based model for accurate crowd density estimation.<n>Our EBC framework can improve existing classification-based methods by up to 44.5% on the UCF-QNRF dataset.<n>CLIP-EBC achieves state-of-the-art performance on the NWPU-Crowd test set, with an MAE of 58.2 and an RMSE of 268.5, representing improvements of 8.6% and 13.3% over the previous best method, STEERER.
• Score: 29.570935239024138
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose CLIP-EBC, the first fully CLIP-based model for accurate crowd density estimation. While the CLIP model has demonstrated remarkable success in addressing recognition tasks such as zero-shot image classification, its potential for counting has been largely unexplored due to the inherent challenges in transforming a regression problem, such as counting, into a recognition task. In this work, we investigate and enhance CLIP's ability to count, focusing specifically on the task of estimating crowd sizes from images. Existing classification-based crowd-counting frameworks have significant limitations, including the quantization of count values into bordering real-valued bins and the sole focus on classification errors. These practices result in label ambiguity near the shared borders and inaccurate prediction of count values. Hence, directly applying CLIP within these frameworks may yield suboptimal performance. To address these challenges, we first propose the Enhanced Blockwise Classification (EBC) framework. Unlike previous methods, EBC utilizes integer-valued bins, effectively reducing ambiguity near bin boundaries. Additionally, it incorporates a regression loss based on density maps to improve the prediction of count values. Within our backbone-agnostic EBC framework, we then introduce CLIP-EBC to fully leverage CLIP's recognition capabilities for this task. Extensive experiments demonstrate the effectiveness of EBC and the competitive performance of CLIP-EBC. Specifically, our EBC framework can improve existing classification-based methods by up to 44.5% on the UCF-QNRF dataset, and CLIP-EBC achieves state-of-the-art performance on the NWPU-Crowd test set, with an MAE of 58.2 and an RMSE of 268.5, representing improvements of 8.6% and 13.3% over the previous best method, STEERER. The code and weights are available at https://github.com/Yiming-M/CLIP-EBC.

Related papers

• CyBOKClaw: Human-in-the-Loop CyBOK Mapping for Cybersecurity Curriculum [0.0]
  CyBOKClaw is a retrieval framework for mapping cybersecurity keywords to the Cyber Security Body of Knowledge (CyBOK)<n>It combines query normalization, curated term expansion, concept-level boosts, topic-description enrichment, and domain-sensitive ranking rules.<n>We evaluate the framework using both structural retrieval metrics and an expert-guided top-5 usefulness metric, ECA-5.
  arXiv  Detail & Related papers  (2026-05-23T17:04:31Z)
• Efficient Text Classification with Conformal In-Context Learning [2.566571621858397]
  Large Language Models (LLMs) demonstrate strong in-context learning abilities, yet their effectiveness in text classification depends heavily on prompt design.<n>We present a comprehensive evaluation of Conformal In-Context Learning (CICLe) across diverse NLP classification benchmarks.<n>In terms of efficiency, CICLe reduces the number of shots and prompt length by up to 34.45% and 25.16%, respectively.
  arXiv  Detail & Related papers  (2025-12-05T14:11:44Z)
• Concept Regions Matter: Benchmarking CLIP with a New Cluster-Importance Approach [20.898059440239603]
  Cluster-based Concept Importance (CCI) is a novel interpretability method.<n>CCI sets a new state of the art on faithfulness benchmarks.<n>We present a comprehensive evaluation of eighteen CLIP variants.
  arXiv  Detail & Related papers  (2025-11-17T05:01:24Z)
• Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework [0.0]
  We investigate the applicability of the CLIP-EBC framework, originally designed for crowd counting, to car object counting using the CARPK dataset.<n> Experimental results show that our model achieves second-best performance compared to existing methods.
  arXiv  Detail & Related papers  (2025-07-11T00:58:54Z)
• Offline Learning for Combinatorial Multi-armed Bandits [56.96242764723241]
  Off-CMAB is the first offline learning framework for CMAB. Off-CMAB combines pessimistic reward estimations with solvers. Experiments on synthetic and real-world datasets highlight the superior performance of CLCB.
  arXiv  Detail & Related papers  (2025-01-31T16:56:18Z)
• Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation [19.749490092520006]
  Self-Calibrated CLIP (SC-CLIP) is a training-free method that calibrates CLIP to produce finer-language representations. SC-CLIP boosts the performance of vanilla CLIP ViT-L/14 by 6.8 times.
  arXiv  Detail & Related papers  (2024-11-24T15:14:05Z)
• Is Less More? Exploring Token Condensation as Training-free Adaptation for CLIP [43.09801987385207]
  Contrastive language-image pre-training (CLIP) has shown remarkable generalization ability in image classification. CLIP sometimes encounters performance drops on downstream datasets during zero-shot inference. This raises an important question: Is there a training-free approach that can efficiently address CLIP's performance drop in such cases?
  arXiv  Detail & Related papers  (2024-10-16T07:13:35Z)
• Token-based Decision Criteria Are Suboptimal in In-context Learning [2.2973949268669562]
  In-Context Learning (ICL) typically utilizes classification criteria from output probabilities of manually selected label tokens. We argue that such token-based classification criteria lead to suboptimal decision boundaries. We propose Hidden, which renounces token probabilities and uses the nearest centroid on the LM's last hidden states.
  arXiv  Detail & Related papers  (2024-06-24T11:16:26Z)
• AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning [50.78033979438031]
  We first introduce a unified formulation to analyze CLIP-based few-shot learning methods from a perspective of logit bias. Based on analysis of key components, this paper proposes a novel AMU-Tuning method to learn effective logit bias for CLIP-based few-shot classification.
  arXiv  Detail & Related papers  (2024-04-13T10:46:11Z)
• Bayesian Exploration of Pre-trained Models for Low-shot Image Classification [14.211305168954594]
  This work proposes a simple and effective probabilistic model ensemble framework based on Gaussian processes. We achieve the integration of prior knowledge by specifying the mean function with CLIP and the kernel function. We demonstrate that our method consistently outperforms competitive ensemble baselines regarding predictive performance.
  arXiv  Detail & Related papers  (2024-03-30T10:25:28Z)
• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference [11.453253140479166]
  We enhance contrastive language-image pretraining's potential for semantic segmentation. By rethinking self-attention, we find that CLIP can adapt to dense prediction tasks. We replace the traditional self-attention block of CLIP vision encoder's last layer by our CSA module.
  arXiv  Detail & Related papers  (2023-12-04T03:18:46Z)
• MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks [65.86360607693457]
  No-box attacks, where adversaries have no prior knowledge, remain relatively underexplored despite its practical relevance. This work presents a systematic investigation into leveraging large-scale Vision-Language Models (VLMs) as surrogate models for executing no-box attacks. Our theoretical and empirical analyses reveal a key limitation in the execution of no-box attacks stemming from insufficient discriminative capabilities for direct application of vanilla CLIP as a surrogate model. We propose MF-CLIP: a novel framework that enhances CLIP's effectiveness as a surrogate model through margin-aware feature space optimization.
  arXiv  Detail & Related papers  (2023-07-13T08:10:48Z)
• CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet [139.56863124214905]
  We find that fine-tuning performance of CLIP is substantially underestimated. Specifically, CLIP ViT-Base/16 and CLIP ViT-Large/14 can achieve 85.7%,88.0% finetuning Top-1 accuracy on the ImageNet-1K dataset.
  arXiv  Detail & Related papers  (2022-12-12T18:59:59Z)
• Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification [80.98291772215154]
  Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by leveraging clustering-based pseudo labels. We propose a Neighbour Consistency guided Pseudo Label Refinement framework.
  arXiv  Detail & Related papers  (2022-11-30T09:39:57Z)
• DenseCLIP: Extract Free Dense Labels from CLIP [130.3830819077699]
  Contrastive Language-Image Pre-training (CLIP) has made a remarkable breakthrough in open-vocabulary zero-shot image recognition. DenseCLIP+ surpasses SOTA transductive zero-shot semantic segmentation methods by large margins. Our finding suggests that DenseCLIP can serve as a new reliable source of supervision for dense prediction tasks.
  arXiv  Detail & Related papers  (2021-12-02T09:23:01Z)
• Re-Assessing the "Classify and Count" Quantification Method [88.60021378715636]
  "Classify and Count" (CC) is often a biased estimator. Previous works have failed to use properly optimised versions of CC. We argue that, while still inferior to some cutting-edge methods, they deliver near-state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2020-11-04T21:47:39Z)

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.