Related papers: What Makes Pre-Trained Visual Representations Succ…

In recent years, a number of models that learn the relations between vision and language from large datasets have been released. These models perform a variety of tasks, such as answering questions about images, retrieving sentences that…

Vision transformers (ViTs) have gained increasing popularity as they are commonly believed to own higher modeling capacity and representation flexibility, than traditional convolutional networks. However, it is questionable whether such…

Unsupervised object-centric representation (OCR) learning has recently drawn attention as a new paradigm of visual representation. This is because of its potential of being an effective pre-training technique for various downstream tasks in…

In recent years, we have witnessed a considerable increase in performance in image classification tasks. This performance improvement is mainly due to the adoption of deep learning techniques. Generally, deep learning techniques demand a…

Recent advances in 3D perception have shown impressive progress in understanding geometric structures of 3Dshapes and even scenes. Inspired by these advances in geometric understanding, we aim to imbue image-based perception with…

Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive knowledge of the world…

Generic re-usable pre-trained image representation encoders have become a standard component of methods for many computer vision tasks. As visual representations for robots however, their utility has been limited, leading to a recent wave…

Existing computer vision research in categorization struggles with fine-grained attributes recognition due to the inherently high intra-class variances and low inter-class variances. SOTA methods tackle this challenge by locating the most…

Vision-language models pre-trained at large scale have shown unprecedented adaptability and generalization to downstream tasks. Although its discriminative potential has been widely explored, its reliability and uncertainty are still…

Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature of frame prediction; multiple potential futures can arise…

Prediction is an appealing objective for self-supervised learning of behavioral skills, particularly for autonomous robots. However, effectively utilizing predictive models for control, especially with raw image inputs, poses a number of…

Frozen pretrained models have become a viable alternative to the pretraining-then-finetuning paradigm for transfer learning. However, with frozen models there are relatively few parameters available for adapting to downstream tasks, which…

Representation learning based on multi-task pretraining has become a powerful approach in many domains. In particular, task-aware representation learning aims to learn an optimal representation for a specific target task by sampling data…

This paper presents a detailed study of improving visual representations for vision language (VL) tasks and develops an improved object detection model to provide object-centric representations of images. Compared to the most widely used…

Vision transformers (ViT) have demonstrated impressive performance across various machine vision problems. These models are based on multi-head self-attention mechanisms that can flexibly attend to a sequence of image patches to encode…

We study how visual representations pre-trained on diverse human video data can enable data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a visual representation using the Ego4D human video dataset…

Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely…

Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition. Learning invariances makes models more robust and practical to use in real-world scenarios. Since data…

The specification of the action space plays a pivotal role in imitation-based robotic manipulation policy learning, fundamentally shaping the optimization landscape of policy learning. While recent advances have focused heavily on scaling…

Recent work in visual representation learning for robotics demonstrates the viability of learning from large video datasets of humans performing everyday tasks. Leveraging methods such as masked autoencoding and contrastive learning, these…