相关论文: Self-supervised visual feature learning with curri…

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we…

Recent work has shown that self-supervised pre-training leads to improvements over supervised learning on challenging visual recognition tasks. CLIP, an exciting new approach to learning with language supervision, demonstrates promising…

Recent self-supervised video representation learning methods have found significant success by exploring essential properties of videos, e.g. speed, temporal order, etc. This work exploits an essential yet under-explored property of videos,…

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…

Machine Learning and Inference methods have become ubiquitous in our attempt to induce more abstract representations of natural language text, visual scenes, and other messy, naturally occurring data, and support decisions that depend on…

Recent work on few-shot learning \cite{tian2020rethinking} showed that quality of learned representations plays an important role in few-shot classification performance. On the other hand, the goal of self-supervised learning is to recover…

Graph self-supervised learning has gained increasing attention due to its capacity to learn expressive node representations. Many pretext tasks, or loss functions have been designed from distinct perspectives. However, we observe that…

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, and anomaly…

We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervised learning have…

When faced with learning challenging new tasks, humans often follow sequences of steps that allow them to incrementally build up the necessary skills for performing these new tasks. However, in machine learning, models are most often…

Supervised learning demands large amounts of precisely annotated data to achieve promising results. Such data curation is labor-intensive and imposes significant overhead regarding time and costs. Self-supervised learning (SSL) partially…

Self-supervision has demonstrated to be an effective learning strategy when training target tasks on small annotated data-sets. While current research focuses on creating novel pretext tasks to learn meaningful and reusable representations…

Establishing visual correspondence across images is a challenging and essential task. Recently, an influx of self-supervised methods have been proposed to better learn representations for visual correspondence. However, we find that these…

Self-supervised learning has significantly improved the performance of many NLP tasks. However, how can self-supervised learning discover useful representations, and why is it better than traditional approaches such as probabilistic models…

Self-supervised feature representations have been shown to be useful for supervised classification, few-shot learning, and adversarial robustness. We show that features obtained using self-supervised learning are comparable to, or better…

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

Deep supervised learning has achieved great success in the last decade. However, its deficiencies of dependence on manual labels and vulnerability to attacks have driven people to explore a better solution. As an alternative,…

We introduce a self-supervised method for learning visual correspondence from unlabeled video. The main idea is to use cycle-consistency in time as free supervisory signal for learning visual representations from scratch. At training time,…