Inductive Learning
Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies
Deep metric learning plays a key role in various machine learning tasks. Most of the previous works have been confined to sampling from a mini-batch, which cannot precisely characterize the global geometry of the embedding space. Although researchers have developed proxy-and classification-based methods to tackle the sampling issue, those methods inevitably incur a redundant computational cost.
Improving Barely Supervised Learning by Discriminating Unlabeled Data with Super-Class
We compare our method with state-of-the-art SSL and BSL methods through extensive experiments on standard SSL benchmarks.
Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning A Proof of Lemma 3.2
We can expand the loss (4), i.e., Table 5 shows more results of our method with different configurations and hyperparameter settings.
Bridging the Gap from Asymmetry Tricks to Decorrelation Principles in Non-contrastive Self-supervised Learning
Currently, there are two approaches to collapse prevention.
PAC-Bayes Analysis Beyond the Usual Bounds
We focus on a stochastic learning model where the learner observes a finite set of training examples and the output of the learning process is a data-dependent distribution over a space of hypotheses. The learned data-dependent distribution is then used to make randomized predictions, and the high-level theme addressed here is guaranteeing the quality of predictions on examples that were not seen during training, i.e. generalization. In this setting the unknown quantity of interest is the expected risk of the data-dependent randomized predictor, for which upper bounds can be derived via a P AC-Bayes analysis, leading to P AC-Bayes bounds. Specifically, we present a basic P AC-Bayes inequality for stochastic kernels, from which one may derive extensions of various known P AC-Bayes bounds as well as novel bounds. We clarify the role of the requirements of fixed'data-free' priors, bounded losses, and i.i.d.
Self-Supervised Learning Disentangled Group Representation as Feature T an Wang
In this paper, we formulate the notion of "good" representation from a group-theoretic view using Higgins' definition of
Evaluation Protocol: The most ambitious aim of self-supervised learning is to create universal visual representations
We thank the reviewers for valuable feedback. Before addressing individual comments, we clarify common concerns. Moreover, "image-level" vs "pixel-level" training has no bearing on the validity of evaluating with Any method that uses a CNN learns more than just "image-level" representations; for Our task is to learn pixel-wise semantic-aware embeddings from scratch. We will update the final version to reflect the full 200 training epochs. We first sample regions, then a fixed number of pixels within chosen regions.