Related papers: No Train, all Gain: Self-Supervised Gradients Impr…
We address the challenging problem of deep representation learning--the efficient adaption of a pre-trained deep network to different tasks. Specifically, we propose to explore gradient-based features. These features are gradients of the…
Fine-tuning pretrained self-supervised language models is widely adopted for transfer learning to downstream tasks. Fine-tuning can be achieved by freezing gradients of the pretrained network and only updating gradients of a newly added…
When training neural networks, the use of Synthetic Gradients (SG) allows layers or modules to be trained without update locking - without waiting for a true error gradient to be backpropagated - resulting in Decoupled Neural Interfaces…
Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets. Self-supervised models trained on…
Unsupervised node representations learnt using contrastive learning-based methods have shown good performance on downstream tasks. However, these methods rely on augmentations that mimic low-pass filters, limiting their performance on tasks…
Automatic differentiation is a key feature of present deep learning frameworks. Moreover, they typically provide various ways to specify custom gradients within the computation graph, which is of particular importance for defining surrogate…
In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this…
Cosine-based softmax losses significantly improve the performance of deep face recognition networks. However, these losses always include sensitive hyper-parameters which can make training process unstable, and it is very tricky to set…
We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an…
Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based approach that uses the…
The standard approach to modern self-supervised learning is to generate random views through data augmentations and minimise a loss computed from the representations of these views. This inherently encourages invariance to the…
The gradients used to train neural networks are typically computed using backpropagation. While an efficient way to obtain exact gradients, backpropagation is computationally expensive, hinders parallelization, and is biologically…
Multi-grained features extracted from convolutional neural networks (CNNs) have demonstrated their strong discrimination ability in supervised person re-identification (Re-ID) tasks. Inspired by them, this work investigates the way of…
Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervised feature learning have focused on either small or highly…
Pretraining convolutional neural networks via self-supervision, and applying them in transfer learning, is an incredibly fast-growing field that is rapidly and iteratively improving performance across practically all image domains.…
Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this…
The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We…
We propose a soft gradient boosting framework for sequential regression that embeds a learnable linear feature transform within the boosting procedure. At each boosting iteration, we train a soft decision tree and learn a linear input…
Un-trained convolutional neural networks have emerged as highly successful tools for image recovery and restoration. They are capable of solving standard inverse problems such as denoising and compressive sensing with excellent results by…
Implicit Neural Representations (INRs) have emerged and shown their benefits over discrete representations in recent years. However, fitting an INR to the given observations usually requires optimization with gradient descent from scratch,…