Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis

• URL: http://arxiv.org/abs/2501.09333v2
• Date: Mon, 07 Apr 2025 18:03:40 GMT
• Title: Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
• Abstract summary: We present a novel approach to make pre-trained Vision Transformers (ViTs) interpretable for fine-grained analysis.<n>Prompt-CAM learns class-specific prompts for a pre-trained ViT and uses the corresponding outputs for classification.
• Score: 29.766516667434026
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We present a simple approach to make pre-trained Vision Transformers (ViTs) interpretable for fine-grained analysis, aiming to identify and localize the traits that distinguish visually similar categories, such as bird species. Pre-trained ViTs, such as DINO, have demonstrated remarkable capabilities in extracting localized, discriminative features. However, saliency maps like Grad-CAM often fail to identify these traits, producing blurred, coarse heatmaps that highlight entire objects instead. We propose a novel approach, Prompt Class Attention Map (Prompt-CAM), to address this limitation. Prompt-CAM learns class-specific prompts for a pre-trained ViT and uses the corresponding outputs for classification. To correctly classify an image, the true-class prompt must attend to unique image patches not present in other classes' images (i.e., traits). As a result, the true class's multi-head attention maps reveal traits and their locations. Implementation-wise, Prompt-CAM is almost a ``free lunch,'' requiring only a modification to the prediction head of Visual Prompt Tuning (VPT). This makes Prompt-CAM easy to train and apply, in stark contrast to other interpretable methods that require designing specific models and training processes. Extensive empirical studies on a dozen datasets from various domains (e.g., birds, fishes, insects, fungi, flowers, food, and cars) validate the superior interpretation capability of Prompt-CAM. The source code and demo are available at https://github.com/Imageomics/Prompt_CAM.

Related papers

• KNN Transformer with Pyramid Prompts for Few-Shot Learning [52.735070934075736]
  Few-Shot Learning aims to recognize new classes with limited labeled data. Recent studies have attempted to address the challenge of rare samples with textual prompts to modulate visual features.
  arXiv  Detail & Related papers  (2024-10-14T07:39:30Z)
• Learning Visual Prompts for Guiding the Attention of Vision Transformers [29.023448448047805]
  This work proposes to learn the visual prompts for guiding the attention of vision transformers. The learned visual prompt, added to any input image would redirect the attention of the pre-trained vision transformer to its spatial location on the image.
  arXiv  Detail & Related papers  (2024-06-05T14:13:38Z)
• A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis [24.531871371861477]
  We realize this idea via a Transformer encoder-decoder inspired by DEtection TRansformer (DETR) We name our approach INterpretable TRansformer (INTR) which is fairly easy to implement and exhibits several compelling properties. Our code and pre-trained models are publicly accessible at the Imageomics Institute GitHub site.
  arXiv  Detail & Related papers  (2023-11-07T17:32:55Z)
• CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypes [93.71909293023663]
  Cross-modality Aligned Prototypes (CAPro) is a unified contrastive learning framework to learn visual representations with correct semantics. CAPro achieves new state-of-the-art performance and exhibits robustness to open-set recognition.
  arXiv  Detail & Related papers  (2023-10-15T07:20:22Z)
• ViT-ReciproCAM: Gradient and Attention-Free Visual Explanations for Vision Transformer [0.0]
  Vision Transformers (ViT) have demonstrated superior performance in various computer vision tasks such as image classification and object detection. Current state-of-the-art solutions for ViT rely on class Attention-Rollout and Relevance techniques. We propose a new gradient-free visual explanation method for ViT, called ViT-ReciproCAM, which does not require attention matrix and gradient information.
  arXiv  Detail & Related papers  (2023-10-04T05:09:50Z)
• Text Descriptions are Compressive and Invariant Representations for Visual Learning [63.3464863723631]
  We show that an alternative approach, in line with humans' understanding of multiple visual features per class, can provide compelling performance in the robust few-shot learning setting. In particular, we introduce a novel method, textit SLR-AVD (Sparse Logistic Regression using Augmented Visual Descriptors). This method first automatically generates multiple visual descriptions of each class via a large language model (LLM), then uses a VLM to translate these descriptions to a set of visual feature embeddings of each image, and finally uses sparse logistic regression to select a relevant subset of these features to classify
  arXiv  Detail & Related papers  (2023-07-10T03:06:45Z)
• Vision Transformers: From Semantic Segmentation to Dense Prediction [139.15562023284187]
  We explore the global context learning potentials of vision transformers (ViTs) for dense visual prediction. Our motivation is that through learning global context at full receptive field layer by layer, ViTs may capture stronger long-range dependency information. We formulate a family of Hierarchical Local-Global (HLG) Transformers, characterized by local attention within windows and global-attention across windows in a pyramidal architecture.
  arXiv  Detail & Related papers  (2022-07-19T15:49:35Z)
• Corrupted Image Modeling for Self-Supervised Visual Pre-Training [103.99311611776697]
  We introduce Corrupted Image Modeling (CIM) for self-supervised visual pre-training. CIM uses an auxiliary generator with a small trainable BEiT to corrupt the input image instead of using artificial mask tokens. After pre-training, the enhancer can be used as a high-capacity visual encoder for downstream tasks.
  arXiv  Detail & Related papers  (2022-02-07T17:59:04Z)
• PreViTS: Contrastive Pretraining with Video Tracking Supervision [53.73237606312024]
  PreViTS is an unsupervised SSL framework for selecting clips containing the same object. PreViTS spatially constrains the frame regions to learn from and trains the model to locate meaningful objects. We train a momentum contrastive (MoCo) encoder on VGG-Sound and Kinetics-400 datasets with PreViTS.
  arXiv  Detail & Related papers  (2021-12-01T19:49:57Z)
• SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning [85.2093650907943]
  We propose SEmantic Guided Attention (SEGA) to teach machines to recognize a new category. SEGA uses semantic knowledge to guide the visual perception in a top-down manner about what visual features should be paid attention to. We show that our semantic guided attention realizes anticipated function and outperforms state-of-the-art results.
  arXiv  Detail & Related papers  (2021-11-08T08:03:44Z)
• CLIP-Adapter: Better Vision-Language Models with Feature Adapters [84.88106370842883]
  We show that there is an alternative path to achieve better vision-language models other than prompt tuning. CLIP-Adapter adopts an additional bottleneck layer to learn new features and performs residual-style feature blending. Experiments and extensive ablation studies on various visual classification tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2021-10-09T11:39:30Z)

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.