PDiscoNet: Semantically consistent part discovery for fine-grained recognition

by   Robert van der Klis, et al.

Fine-grained classification often requires recognizing specific object parts, such as beak shape and wing patterns for birds. Encouraging a fine-grained classification model to first detect such parts and then using them to infer the class could help us gauge whether the model is indeed looking at the right details better than with interpretability methods that provide a single attribution map. We propose PDiscoNet to discover object parts by using only image-level class labels along with priors encouraging the parts to be: discriminative, compact, distinct from each other, equivariant to rigid transforms, and active in at least some of the images. In addition to using the appropriate losses to encode these priors, we propose to use part-dropout, where full part feature vectors are dropped at once to prevent a single part from dominating in the classification, and part feature vector modulation, which makes the information coming from each part distinct from the perspective of the classifier. Our results on CUB, CelebA, and PartImageNet show that the proposed method provides substantially better part discovery performance than previous methods while not requiring any additional hyper-parameter tuning and without penalizing the classification performance. The code is available at https://github.com/robertdvdk/part_detection.


page 3

page 7

page 8

page 9


Interpretable and Accurate Fine-grained Recognition via Region Grouping

We present an interpretable deep model for fine-grained visual recogniti...

Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition

Few-shot, fine-grained classification requires a model to learn subtle, ...

Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification

Deep Neural Network has shown great strides in the coarse-grained image ...

Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches

Fine-grained visual classification (FGVC) is much more challenging than ...

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data

Data mixing augmentation has proved effective in training deep models. R...

Simplified Concrete Dropout – Improving the Generation of Attribution Masks for Fine-grained Classification

Fine-grained classification is a particular case of a classification pro...

VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living

Many attempts have been made towards combining RGB and 3D poses for the ...

Please sign up or login with your details

Forgot password? Click here to reset