Bootstrapping Parallel Anchors for Relative Representations
The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot model stitching across a wide range of applications. Nevertheless, relative representations rely on a certain amount of parallel anchors to be given as input, which can be impractical to obtain in certain scenarios. To overcome this limitation, we propose an optimization-based method to discover new parallel anchors from a limited known set (seed). Our approach can be used to find semantic correspondence between different domains, align their relative spaces, and achieve competitive results in several tasks.
Code (1)
Tasks
Semantic correspondenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving
End-to-end multi-modal planning has become a transformative paradigm in autonomous driving, effectively addressing behavioral multi-modality and the generalization challenge in long-tail scenarios. We propose AnchDrive, …
Autonomous DrivingWeakly Supervised Vision-and-Language Pre-training with Relative Representations
Weakly supervised vision-and-language pre-training (WVLP), which learns cross-modal representations with limited cross-modal supervision, has been shown to effectively reduce the data cost of pre-training while maintaini…
RetrievalImproving Relative Representations with Learned Anchors and Whitened Inner Products
Independently trained neural models typically converge to incompatible latent representations, creating a fundamental barrier to highly modular AI systems. While Relative Representations (RR) address this by mapping abso…
Relative Representations of Latent Spaces enable Efficient Semantic Channel Equalization
In multi-user semantic communication, language mismatche poses a significant challenge when independently trained agents interact. We present a novel semantic equalization algorithm that enables communication between age…
Semantic CommunicationInstant Learning: Parallel Deep Neural Networks and Convolutional Bootstrapping
Although deep neural networks (DNN) are able to scale with direct advances in computational power (e.g., memory and processing speed), they are not well suited to exploit the recent trends for parallel architectures. In …