Related papers: On the robustness of self-supervised representatio…
Vision (image and video) - Language (VL) pre-training is the recent popular paradigm that achieved state-of-the-art results on multi-modal tasks like image-retrieval, video-retrieval, visual question answering etc. These models are trained…
Vision Transformers (ViTs) have gained significant popularity in recent years and have proliferated into many applications. However, their behavior under different learning paradigms is not well explored. We compare ViTs trained through…
The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to…
An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical…
Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. However, discovering objects in an image with no supervision is…
Self-supervised learning (SSL) holds promise in leveraging large amounts of unlabeled data. However, the success of popular SSL methods has limited on single-centric-object images like those in ImageNet and ignores the correlation among the…
Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…
Unsupervised representation learning methods like SwAV are proved to be effective in learning visual semantics of a target dataset. The main idea behind these methods is that different views of a same image represent the same semantics. In…
Existing few-shot learning (FSL) methods rely on training with a large labeled dataset, which prevents them from leveraging abundant unlabeled data. From an information-theoretic perspective, we propose an effective unsupervised FSL method,…
In self-supervised learning, a system is tasked with achieving a surrogate objective by defining alternative targets on a set of unlabeled data. The aim is to build useful representations that can be used in downstream tasks, without costly…
Self-supervised contrastive learning has demonstrated great potential in learning visual representations. Despite their success in various downstream tasks such as image classification and object detection, self-supervised pre-training for…
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…
Despite the impressive advancements achieved through vision-and-language pretraining, it remains unclear whether this joint learning paradigm can help understand each individual modality. In this work, we conduct a comparative analysis of…
Human decision-making often relies on visual information from multiple perspectives or views. In contrast, machine learning-based object recognition utilizes information from a single image of the object. However, the information conveyed…
In this paper, we focus on the self-supervised learning of visual correspondence using unlabeled videos in the wild. Our method simultaneously considers intra- and inter-video representation associations for reliable correspondence…
Self-supervised learning is an effective way for label-free model pre-training, especially in the video domain where labeling is expensive. Existing self-supervised works in the video domain use varying experimental setups to demonstrate…
A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled…
Recent years have seen rapid development in Information Extraction, as well as its subtask, Relation Extraction. Relation Extraction is able to detect semantic relations between entities in sentences. Currently, many efficient approaches…
The sense of touch is fundamental in several manipulation tasks, but rarely used in robot manipulation. In this work we tackle the problem of learning rich touch features from cross-modal self-supervision. We evaluate them identifying…
Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on…