Related papers: What makes instance discrimination good for transf…

In response to an object presentation, supervised learning schemes generally respond with a parsimonious label. Upon a similar presentation we humans respond again with a label, but are flooded, in addition, by a myriad of associations. A…

We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is…

Text style transfer has gained increasing attention from the research community over the recent years. However, the proposed approaches vary in many ways, which makes it hard to assess the individual contribution of the model components. In…

Pre-trained language models are still far from human performance in tasks that need understanding of properties (e.g. appearance, measurable quantity) and affordances of everyday objects in the real world since the text lacks such…

In this work, we evaluate contrastive models for the task of image retrieval. We hypothesise that models that are learned to encode semantic similarity among instances via discriminative learning should perform well on the task of image…

Large-scale multimodal representation learning successfully optimizes for zero-shot transfer at test time. Yet the standard pretraining paradigm (contrastive learning on large amounts of image-text data) does not explicitly encourage…

Self-supervised representation learning has seen remarkable progress in the last few years. More recently, contrastive instance learning has shown impressive results compared to its supervised learning counterparts. However, even with the…

Supervised learning with large scale labeled datasets and deep layered models has made a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers generalization issues under the presence of a domain…

If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem domain. However, this is often not how models are trained and…

Instance segmentation is an important computer vision problem which remains challenging despite impressive recent advances due to deep learning-based methods. Given sufficient training data, fully supervised methods can yield excellent…

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that…

Transfer learning from supervised ImageNet models has been frequently used in medical image analysis. Yet, no large-scale evaluation has been conducted to benchmark the efficacy of newly-developed pre-training techniques for medical image…

Visual object tracking performance has been dramatically improved in recent years, but some severe challenges remain open, like distractors and occlusions. We suspect the reason is that the feature representations of the tracking targets…

The tremendous success of ImageNet-trained deep features on a wide range of transfer tasks begs the question: what are the properties of the ImageNet dataset that are critical for learning good, general-purpose features? This work provides…

In practice, it is very demanding and sometimes impossible to collect datasets of tagged data large enough to successfully train a machine learning model, and one possible solution to this problem is transfer learning. This study aims to…

Object detection is one of the major problems in computer vision, and has been extensively studied. Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least…

Contrastive learning is a highly effective method for learning representations from unlabeled data. Recent works show that contrastive representations can transfer across domains, leading to simple state-of-the-art algorithms for…

Learning with the \textit{instance-dependent} label noise is challenging, because it is hard to model such real-world noise. Note that there are psychological and physiological evidences showing that we humans perceive instances by…

Contrastive learning is commonly applied to self-supervised learning, and has been shown to outperform traditional approaches such as the triplet loss and N-pair loss. However, the requirement of large batch sizes and memory banks has made…

In transfer learning, only the last part of the networks - the so-called head - is often fine-tuned. Representation similarity analysis shows that the most significant change still occurs in the head even if all weights are updatable.…