BRIEF: Backward Reduction of CNNs with Information Flow Analysis
This work addresses model compression for efficient deployment in resource-constrained environments, offering incremental improvements over existing techniques.
The paper tackles the problem of reducing CNN model size by proposing BRIEF, a backward reduction algorithm that removes redundant neural channels based on information flow analysis, achieving a 32.3% reduction on ResNet-34 and additional reductions on SqueezeNet and MobileNet with minimal performance loss.
This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-zero weighting parameters (redundant neural channels) of a network by considering its dynamic behavior, which traditional model-compaction techniques cannot achieve. With the aid of our proposed algorithm, we achieve significant model reduction on ResNet-34 in the ImageNet scale (32.3% reduction), which is 3X better than the previous result (10.8%). Even for highly optimized models such as SqueezeNet and MobileNet, we can achieve additional 10.81% and 37.56% reduction, respectively, with negligible performance degradation.