paper-with-me

Papers

CLIP-Count: Towards Text-Guided Zero-Shot Object Counting

2023-05-12 · Ruixiang Jiang, Lingbo Liu, Changwen Chen

Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to downstream tasks such as object detection and segmentation. Adapting these models for object counting, however, remains a formidable challenge. In this study, we first investigate transferring vision-language models (VLMs) for class-agnostic object counting. Specifically, we propose CLIP-Count, the first end-to-end pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner. To align the text embedding with dense visual features, we introduce a patch-text contrastive loss that guides the model to learn informative patch-level visual representations for dense prediction. Moreover, we design a hierarchical patch-text interaction module to propagate semantic information across different resolution levels of visual features. Benefiting from the full exploitation of the rich image-text alignment knowledge of pretrained VLMs, our method effectively generates high-quality density maps for objects-of-interest. Extensive experiments on FSC-147, CARPK, and ShanghaiTech crowd counting datasets demonstrate state-of-the-art accuracy and generalizability of the proposed method. Code is available: https://github.com/songrise/CLIP-Count.

📄 PDF Abstract BibTeX arXiv:2305.07304

Code (1)

songrise/clip-count 공식 구현 pytorch

Tasks

Cross-Part Crowd CountingCross-Part EvaluationCrowd CountingObjectObject Countingobject-detectionObject DetectionZero-Shot Counting

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models

2024-10-29 · Lu Yu, Haiyang Zhang, Changsheng Xu

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g. CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible…

Adversarial RobustnessAll

Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP

2023-10-02 · Zixiang Chen, Yihe Deng, Yuanzhi Li, Quanquan Gu

Multi-modal learning has become increasingly popular due to its ability to leverage information from different data sources (e.g., text and images) to improve the model performance. Recently, CLIP has emerged as an effec…

Image GenerationRepresentation LearningZero-Shot Learning

Zero-Shot Visual Classification with Guided Cropping

2023-09-12 · Piyapat Saranrittichai, Mauricio Munoz, Volker Fischer, Chaithanya Kumar Mummadi

Pretrained vision-language models, such as CLIP, show promising zero-shot performance across a wide variety of datasets. For closed-set classification tasks, however, there is an inherent limitation: CLIP image encoders …

ClassificationObjectobject-detectionObject Detection+3

Complementary Text-Guided Attention for Zero-Shot Adversarial Robustness

2026-03-19 · Lu Yu, Haiyang Zhang, Changsheng Xu arxiv

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g., CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptibl…

Adversarial Robustness

Understanding Zero-Shot Adversarial Robustness for Large-Scale Models

2022-12-14 · Chengzhi Mao, Scott Geng, Junfeng Yang, Xin Wang 외

Pretrained large-scale vision-language models like CLIP have exhibited strong generalization over unseen tasks. Yet imperceptible adversarial perturbations can significantly reduce CLIP's performance on new tasks. In thi…

Adversarial RobustnessContrastive LearningVisual Prompt Tuning