Related papers: RePre: Improving Self-Supervised Vision Transforme…

This paper presents an efficient multi-scale vision Transformer, called ResT, that capably served as a general-purpose backbone for image recognition. Unlike existing Transformer methods, which employ standard Transformer blocks to tackle…

Contrastive learning methods in self-supervised settings have primarily focused on pre-training encoders, while decoders are typically introduced and trained separately for downstream dense prediction tasks. However, this conventional…

We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as…

Change captioning aims to describe the difference between a pair of similar images. Its key challenge is how to learn a stable difference representation under pseudo changes caused by viewpoint change. In this paper, we address this by…

While contrastive learning is proven to be an effective training strategy in computer vision, Natural Language Processing (NLP) is only recently adopting it as a self-supervised alternative to Masked Language Modeling (MLM) for improving…

We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures…

Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT). This is mainly due to the compositionality of the target space, where…

In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper, we propose a novel multi-task deep network to learn…

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the…

The success of deep learning is usually accompanied by the growth in neural network depth. However, the traditional training method only supervises the neural network at its last layer and propagates the supervision layer-by-layer, which…

Recent progress of self-supervised visual representation learning has achieved remarkable success on many challenging computer vision benchmarks. However, whether these techniques can be used for domain adaptation has not been explored. In…

We present a new framework for self-supervised representation learning by formulating it as a ranking problem in an image retrieval context on a large number of random views (augmentations) obtained from images. Our work is based on two…

We introduce ReConvNet, a recurrent convolutional architecture for semi-supervised video object segmentation that is able to fast adapt its features to focus on any specific object of interest at inference time. Generalization to new…

Contrastive self-supervised learning (CSL) based on instance discrimination typically attracts positive samples while repelling negatives to learn representations with pre-defined binary self-supervision. However, vanilla CSL is inadequate…

We develop a novel transfer learning framework to tackle the challenge of limited training data in image reconstruction problems. The proposed framework consists of two training steps, both of which are formed as bi-level optimizations. In…

In recent years, self-supervised contrastive learning has emerged as a distinguished paradigm in the artificial intelligence landscape. It facilitates unsupervised feature learning through contrastive delineations at the instance level.…

Contrastive learning has demonstrated great effectiveness in representation learning especially for image classification tasks. However, there is still a shortage in the studies targeting regression tasks, and more specifically applications…

Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations. However, most of methods mainly focus on the instance level information…

Understanding the severity of conditions shown in images in medical diagnosis is crucial, serving as a key guide for clinical assessment, treatment, as well as evaluating longitudinal progression. This paper proposes Con- PrO: a novel…

Although backpropagation is widely accepted as a training algorithm for artificial neural networks, researchers are always looking for inspiration from the brain to find ways with potentially better performance. Forward-Forward is a novel…