The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification

Abstract

Key for solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed specifically to learn part-level discriminate feature representations. In this paper, we show it is possible to cultivate subtle details without the need for overly complicated network designs or training mechanisms -- a single loss is all it takes. The main trick lies with how we delve into individual feature channels early on, as opposed to the convention of starting from a consolidated feature map. The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component. The discriminality component forces all feature channels belonging to the same class to be discriminative, through a novel channel-wise attention mechanism. The diversity component additionally constraints channels so that they become mutually exclusive on spatial-wise. The end result is therefore a set of feature channels that each reflects different locally discriminative regions for a specific class. The MC-Loss can be trained end-to-end, without the need for any bounding-box/part annotations, and yields highly discriminative regions during inference. Experimental results show our MC-Loss when implemented on top of common base networks can achieve state-of-the-art performance on all four fine-grained categorization datasets (CUB-Birds, FGVC-Aircraft, Flowers-102, and Stanford-Cars). Ablative studies further demonstrate the superiority of MC-Loss when compared with other recently proposed general-purpose losses for visual classification, on two different base networks. Code available at https://github.com/dongliangchang/Mutual-Channel-Loss

TIP2020. Code available at https://github.com/dongliangchang/Mutual-Channel-Loss

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Squeeze-and-Excitation Networks
• Fine-Grained Visual Classification of Aircraft
• Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
• Object-Part Attention Model for Fine-grained Image Classification
• Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
• Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval
• Multi-Graph Transformer for Free-Hand Sketch Recognition

Cited by in corpus (29)

• AI based Service Management for 6G Green Communications
• BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
• Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification
• SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization
• Part-guided Relational Transformers for Fine-grained Visual Recognition
• CholecTriplet2021: A benchmark challenge for surgical action triplet recognition
• Computer Vision on X-ray Data in Industrial Production and Security Applications: A Comprehensive Survey
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
• PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection
• Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
• Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition
• A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis
• Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
• DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference
• Fine-Grained Image Analysis with Deep Learning: A Survey
• M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition
• Your "Flamingo" is My "Bird": Fine-Grained, or Not
• Deep Self-Supervised Representation Learning for Free-Hand Sketch
• Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted Pooling
• Grad-CAM guided channel-spatial attention module for fine-grained visual classification
• Knowledge Transfer Based Fine-grained Visual Classification
• Sequential Random Network for Fine-grained Image Classification
• Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features
• ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification
• Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization
• Human-Understandable Decision Making for Visual Recognition
• Interpretable Attention Guided Network for Fine-grained Visual Classification
• Enhancing Fine-Grained Visual Recognition in the Low-Data Regime Through Feature Magnitude Regularization