Naturally Computed Scale Invariance in the Residual Stream of ResNet18
An important capacity in visual object recognition is invariance to image-altering variables which leave the identity of objects unchanged, such as lighting, rotation, and scale. How do neural networks achieve this? Prior mechanistic interpretability research has illuminated some invariance-building circuitry in InceptionV1, but the results are limited and networks with different architectures have remained largely unexplored. This work investigates ResNet18 with a particular focus on its residual stream, an architectural component which InceptionV1 lacks. We observe that many convolutional channels in intermediate blocks exhibit scale invariant properties, computed by the element-wise residual summation of scale equivariant representations: the block input's smaller-scale copy with the block pre-sum output's larger-scale copy. Through subsequent ablation experiments, we attempt to causally link these neural properties with scale-robust object recognition behavior. Our tentative findings suggest how the residual stream computes scale invariance and its possible role in behavior. Code is available at: https://github.com/cest-andre/residual-stream-interp
Code (1)
Tasks
Object RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Interpreting the Residual Stream of ResNet18
A mechanistic understanding of the computations learned by deep neural networks (DNNs) is far from complete. In the domain of visual object recognition, prior research has illuminated inner workings of InceptionV1, but D…
Object RecognitionTemporal Deformable Residual Networks for Action Segmentation in Videos
This paper is about temporal segmentation of human actions in videos. We introduce a new model -- temporal deformable residual network (TDRN) -- aimed at analyzing video intervals at multiple temporal scales for labelin…
Action SegmentationSegmentationGrounding inductive biases in natural images:invariance stems from variations in data
To perform well on unseen and potentially out-of-distribution samples, it is desirable for machine learning models to have a predictable response with respect to transformations affecting the factors of variation of the …
Data AugmentationTranslationGrounding inductive biases in natural images: invariance stems from variations in data
To perform well on unseen and potentially out-of-distribution samples, it is desirable for machine learning models to have a predictable response with respect to transformations affecting the factors of variation of the …
Data AugmentationTranslationRDQ: Residual Distribution Quantization for Large Language Models
Post-training quantization (PTQ) of large language models degrades sharply below 4-bit precision. We identify the root cause as residual stream distributional drift: quantization noise injected at each transformer layer …