A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis

TL;DR

It is shown that INTR intrinsically encourages each class to attend distinctively; the cross-attention weights thus provide a faithful interpretation of the prediction, making it particularly suitable for fine-grained classification and analysis, which it demonstrates on eight datasets.

Abstract

We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a proactive approach, asking each class to search for itself in an image. We realize this idea via a Transformer encoder-decoder inspired by DEtection TRansformer (DETR). We learn "class-specific" queries (one for each class) as input to the decoder, enabling each class to localize its patterns in an image via cross-attention. We name our approach INterpretable TRansformer (INTR), which is fairly easy to implement and exhibits several compelling properties. We show that INTR intrinsically encourages each class to attend distinctively; the cross-attention weights thus provide a faithful interpretation of the prediction. Interestingly, via "multi-head" cross-attention, INTR could identify different "attributes" of a class, making it particularly suitable for fine-grained classification and analysis, which we demonstrate on eight datasets. Our code and pre-trained models are publicly accessible at the Imageomics Institute GitHub site: https://github.com/Imageomics/INTR.

Figures (23)

• Figure 1: Illustration of INTR. We show four images (row-wise) of the same bird species Painted Bunting and the eight-head cross-attention maps (column-wise) triggered by the query of the ground-truth class. Each head is learned to attend to a different (across columns) but consistent (across rows) semantic cue in the image that is useful to recognize this bird species (e.g., attributes). The exception is the last row, which shows inconsistent attention. Indeed, this is a misclassified case, showcasing how INTR interprets (wrong) predictions.
• Figure 2: Model architecture of INTR. See \ref{['ss_idea']} for details.
• Figure 3: Comparison to interpretable models. We show the responses of the top three cross-attention heads or prototypes (row-wise) of each method (column-wise) in a Painted Bunting image.
• Figure 4: INTR on all eight datasets. We show the top four cross-attention maps per test example triggered by the ground-truth classes (based on the peak un-normalized attention weights in the maps). As the indices of the top maps may not be the same across test examples, the attributes may not be the same in each column.
• Figure 5: INTR can identify tiny image manipulations that distinguish between classes. On the top, we remove the red spots of the Red-winged Blackbird. After that, INTR cannot correctly classify the image --- the parentheses in the Answer column highlight the predicted classes. On the bottom, we change the color of the bird's belly (Baltimore Oriole) to make it look like Orchard Oriole. After that, INTR would misclassify it as Orchard Oriole. Both results demonstrate INTR's sensitivity to visual attributes.