Pooling is neither necessary nor sufficient for appropriate deformation stability in CNNs

ICLR 2019 Avraham RudermanNeil C. RabinowitzAri S. MorcosDaniel Zoran

Many of our core assumptions about how neural networks operate remain empirically untested. One common assumption is that convolutional neural networks need to be stable to small translations and deformations to solve image recognition tasks... (read more)

PDF Abstract


No code implementations yet. Submit your code now

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.