CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections

• URL: http://arxiv.org/abs/2411.19346v3
• Date: Thu, 10 Apr 2025 11:09:41 GMT
• Title: CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections
• Authors: Mohamed Fazli Imam, Rufael Fedaku Marew, Jameel Hassan, Mustansar Fiaz, Alham Fikri Aji, Hisham Cholakkal,
• Abstract summary: We propose a label-free prompt-tuning method to enhance CLIP-based image classification performance using unlabeled images.<n>Our framework, NoLA (No Labels Attached), achieves an average absolute gain of 3.6% over the state-of-the-art LaFTer.
• Score: 22.32157080294386
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In the era of foundation models, CLIP has emerged as a powerful tool for aligning text & visual modalities into a common embedding space. However, the alignment objective used to train CLIP often results in subpar visual features for fine-grained tasks. In contrast, SSL-pretrained models like DINO excel at extracting rich visual features due to their specialized training paradigm. Yet, these SSL models require an additional supervised linear probing step, which relies on fully labeled data which is often expensive and difficult to obtain at scale. In this paper, we propose a label-free prompt-tuning method that leverages the rich visual features of self-supervised learning models (DINO) and the broad textual knowledge of large language models (LLMs) to largely enhance CLIP-based image classification performance using unlabeled images. Our approach unfolds in three key steps: (1) We generate robust textual feature embeddings that more accurately represent object classes by leveraging class-specific descriptions from LLMs, enabling more effective zero-shot classification compared to CLIP's default name-specific prompts. (2) These textual embeddings are then used to produce pseudo-labels to train an alignment module that integrates the complementary strengths of LLM description-based textual embeddings & DINO's visual features. (3) Finally, we prompt-tune CLIP's vision encoder through DINO-assisted supervision using the trained alignment module. This three-step process allows us to harness the best of visual & textual foundation models, resulting in a powerful and efficient approach that surpasses state-of-the-art label-free classification methods. Notably, our framework, NoLA (No Labels Attached), achieves an average absolute gain of 3.6% over the state-of-the-art LaFTer across 11 diverse image classification datasets. Our code & models can be found at https://github.com/fazliimam/NoLA.

Related papers

• DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment [20.953645420787527]
  We train a CLIP-like model with only a fraction of the computational cost compared to CLIP. We achieve state-of-the-art results in zero-shot classification and open-vocabulary semantic segmentation.
  arXiv  Detail & Related papers  (2024-12-20T20:46:48Z)
• LMSeg: Unleashing the Power of Large-Scale Models for Open-Vocabulary Semantic Segmentation [16.864086165056698]
  Existing open-vocabulary approaches leverage vision-language models, such as CLIP, to align visual features with rich semantic features acquired through pre-training on large-scale vision-language datasets. We propose to alleviate the issues by leveraging multiple large-scale models to enhance the alignment between fine-grained visual features and enriched linguistic features. Our method achieves state-of-the-art performance across all major open-vocabulary segmentation benchmarks.
  arXiv  Detail & Related papers  (2024-11-30T05:49:42Z)
• LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts [17.925954549422567]
  We propose LatteCLIP, an unsupervised method for fine-tuning CLIP models on classification with known class names in custom domains. Our method leverages Large Multimodal Models (LMMs) to generate expressive textual descriptions for both individual images and groups of images. Our experiments on 10 domain-specific datasets show that LatteCLIP outperforms pre-trained zero-shot methods by an average improvement of +4.74 points in top-1 accuracy.
  arXiv  Detail & Related papers  (2024-10-10T17:59:59Z)
• CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation [12.994898879803642]
  The CLIP-Decoder is a novel method based on the state-of-the-art ML-Decoder attention-based head. We introduce multi-modal representation learning in CLIP-Decoder, utilizing the text encoder to extract text features and the image encoder for image feature extraction. Our method achieves an absolute increase of 3.9% in performance compared to existing methods for zero-shot learning multi-label classification tasks.
  arXiv  Detail & Related papers  (2024-06-21T02:19:26Z)
• Better Call SAL: Towards Learning to Segment Anything in Lidar [63.9984147657437]
  We propose a text-promptable zero-shot model for segmenting and classifying any object in Lidar. We utilize 2D vision foundation models to generate 3D supervision for free'' using pseudo-labels. Our model achieves $91%$ in terms of class-agnostic and $54%$ in terms of zero-shot Lidar Panopticon.
  arXiv  Detail & Related papers  (2024-03-19T19:58:54Z)
• UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding [90.74967596080982]
  This paper extends Contrastive Language-Image Pre-training (CLIP) with multi-granularity alignment. We develop a Unified Multi-Granularity learning framework, termed UMG-CLIP, which simultaneously empowers the model with versatile perception abilities. With parameter efficient tuning, UMG-CLIP surpasses current widely used CLIP variants and achieves state-of-the-art performance on diverse image understanding benchmarks.
  arXiv  Detail & Related papers  (2024-01-12T06:35:09Z)
• CLAMP: Contrastive LAnguage Model Prompt-tuning [89.96914454453791]
  We show that large language models can achieve good image classification performance when adapted this way. Our approach beats state-of-the-art mLLMs by 13% and slightly outperforms contrastive learning with a custom text model.
  arXiv  Detail & Related papers  (2023-12-04T05:13:59Z)
• CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement [65.47237619200442]
  Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. We augment CLIP training with task-specific vision models from model zoos to improve its visual representations. This simple setup shows substantial improvements of up to 16.3% across different vision tasks.
  arXiv  Detail & Related papers  (2023-10-21T20:20:13Z)
• CLIP Is Also a Good Teacher: A New Learning Framework for Inductive Zero-shot Semantic Segmentation [6.181169909576527]
  Generalized Zero-shot Semantic aims to segment both seen and unseen categories only under the supervision of the seen ones. Existing methods adopt the large-scale Vision Language Models (VLMs) which obtain outstanding zero-shot performance. We propose CLIP-ZSS (Zero-shot Semantic), a training framework that enables any image encoder designed for closed-set segmentation applied in zero-shot and open-vocabulary tasks.
  arXiv  Detail & Related papers  (2023-10-03T09:33:47Z)
• Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment [53.2701026843921]
  Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
  arXiv  Detail & Related papers  (2023-08-24T17:56:46Z)
• CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation [19.208559353954833]
  This paper explores the potential of Contrastive Language-Image Pre-training models (CLIP) to localize different categories with only image-level labels. To efficiently generate high-quality segmentation masks from CLIP, we propose a novel WSSS framework called CLIP-ES.
  arXiv  Detail & Related papers  (2022-12-16T06:23:59Z)
• Masked Unsupervised Self-training for Zero-shot Image Classification [98.23094305347709]
  Masked Unsupervised Self-Training (MUST) is a new approach which leverages two different and complimentary sources of supervision: pseudo-labels and raw images. MUST improves upon CLIP by a large margin and narrows the performance gap between unsupervised and supervised classification.
  arXiv  Detail & Related papers  (2022-06-07T02:03:06Z)

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.