arXiv cs.CV
· Papers
Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks
arXiv:2509.23926v4 Announce Type: replace Abstract: Empirical evidence shows that deep vision networks often represent concepts as directions in latent space with concept information written along directional components in the vector representation of the input. However, the mechanism to encode (write) and decode (read