Related papers: Diminishing Returns in Self-Supervised Learning
Self-supervised pre-training for 3D vision has drawn increasing research interest in recent years. In order to learn informative representations, a lot of previous works exploit invariances of 3D features, e.g., perspective-invariance…
Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision. However, existing approaches apply random or ad hoc masking…
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…
Finetuning pretrained models occurs in a low-dimensional subspace of the full parameter space. Prior work has focused on characterizing this optimization subspace, but largely ignored the complementary question: why do certain directions…
Supervised machine learning provides state-of-the-art solutions to a wide range of computer vision problems. However, the need for copious labelled training data limits the capabilities of these algorithms in scenarios where such input is…
Self-supervised speech representation learning has recently been a prosperous research topic. Many algorithms have been proposed for learning useful representations from large-scale unlabeled data, and their applications to a wide range of…
Transfer learning is the predominant paradigm for training deep networks on small target datasets. Models are typically pretrained on large ``upstream'' datasets for classification, as such labels are easy to collect, and then finetuned on…
Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data structure or context by solving a pretext task.…
The past year has witnessed a rapid development of masked image modeling (MIM). MIM is mostly built upon the vision transformers, which suggests that self-supervised visual representations can be done by masking input image parts while…
Gradient descent typically converges to a single minimum of the training loss without mechanisms to explore alternative minima that may generalize better. Searching for diverse minima directly in high-dimensional parameter space is…
This paper demonstrates a self-supervised framework for learning voxel-wise coarse-to-fine representations tailored for dense downstream tasks. Our approach stems from the observation that existing methods for hierarchical representation…
Fine-grained image classification involves identifying different subcategories of a class which possess very subtle discriminatory features. Fine-grained datasets usually provide bounding box annotations along with class labels to aid the…
Pretext-based self-supervised learning learns the semantic representation via a handcrafted pretext task over unlabeled data and then uses the learned representation for downstream tasks, which effectively reduces the sample complexity of…
The joint optimization of the reconstruction and classification error is a hard non convex problem, especially when a non linear mapping is utilized. In order to overcome this obstacle, a novel optimization strategy is proposed, in which a…
This work investigates the unexplored usability of self-supervised representation learning in the direction of functional knowledge transfer. In this work, functional knowledge transfer is achieved by joint optimization of self-supervised…
Self-supervised pretraining has been shown to yield powerful representations for transfer learning. These performance gains come at a large computational cost however, with state-of-the-art methods requiring an order of magnitude more…
The large adoption of the self-attention (i.e. transformer model) and BERT-like training principles has recently resulted in a number of high performing models on a large panoply of vision-and-language problems (such as Visual Question…
Recent advances in self-supervised learning (SSL) have largely closed the gap with supervised ImageNet pretraining. Despite their success these methods have been primarily applied to unlabeled ImageNet images, and show marginal gains when…
Self-supervised pre-training using so-called "pretext" tasks has recently shown impressive performance across a wide range of modalities. In this work, we advance self-supervised learning from permutations, by pre-training a model to…
Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature extractors or model initializers before fine-tuning. The former severely limits the…