Learning Where to Learn in Cross-View Self-Supervised Learning

Lang Huang, Shan You, Fei Wang, Chen Qian, Mingkai Zheng, Toshihiko Yamasaki

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• LayneH/LEWEL — marked official in Papers with Code

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Self-supervised learning (SSL) has made enormous progress and largely narrowed the gap with the supervised ones, where the representation learning is mainly guided by a projection into an embedding space. During the projection, current methods simply adopt uniform aggregation of pixels for embedding; however, this risks involving objectirrelevant nuisances and spatial misalignment for different augmentations. In this paper, we present a new approach, Learning Where to Learn (LEWEL), to adaptively aggregate spatial information of features, so that the projected embeddings could be exactly aligned and thus guide the feature learning better. Concretely, we reinterpret the projection head in SSL as a per-pixel projection and predict a set of spatial alignment maps from the original features by this weight-sharing projection head. A spectrum of aligned embeddings is thus obtained by aggregating the features with spatial weighting according to these alignment maps. As a result of this adaptive alignment, we observe substantial improvements on both image-level prediction and dense prediction at the same time: LEWEL improves MoCov2 [15] by 1.6%/1.3%/0.5%/0.4% points, improves BYOL [14] by 1.3%/1.3%/0.7%/0.6% points, on ImageNet linear/semi-supervised classification, Pascal VOC semantic segmentation, and object detection, respectively. †

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.14898")
get_code_for_paper("2203.14898")
have("2203.14898")

Connect an agent — have() is free.