Related papers: LayerLock: Non-collapsing Representation Learning …
Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks…
Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…
Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and the success of visual models trained contrastively with language. While these factors have…
Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training models to output features for downstream use, we train them to…
We study how to transfer representations pretrained on source tasks to target tasks in visual percept based RL. We analyze two popular approaches: freezing or finetuning the pretrained representations. Empirical studies on a set of popular…
Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient robot learning from visual observations. Yet the current approaches typically train a single model end-to-end for learning both visual…
We propose an end-to-end learned image data hiding framework that embeds and extracts secrets in the latent representations of a generic neural compressor. By leveraging a perceptual loss function in conjunction with our proposed message…
Recent advances in autonomous robotic technologies have highlighted the growing need for precise environmental analysis. LiDAR semantic segmentation has gained attention to accomplish fine-grained scene understanding by acting directly on…
We address the Continual Learning (CL) problem, wherein a model must learn a sequence of tasks from non-stationary distributions while preserving prior knowledge upon encountering new experiences. With the advancement of foundation models,…
Self-supervised learning (SSL) has emerged as a powerful technique for learning visual representations. While recent SSL approaches achieve strong results in global image understanding, they are limited in capturing the structured…
Recent pre-trained language models (PLMs) achieved great success on many natural language processing tasks through learning linguistic features and contextualized sentence representation. Since attributes captured in stacked layers of PLMs…
Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different…
Vision-language foundation models such as CLIP have achieved tremendous results in global vision-language alignment, but still show some limitations in creating representations for specific image regions. % To address this problem, we…
Modern deep learning models have demonstrated outstanding performance on discovering the underlying mechanisms when both visual appearance and intrinsic relations (e.g., causal structure) data are sufficient, such as Disentangled…
With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…
The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the…
While the Self-Attention mechanism in the Transformer model has proven to be effective in many domains, we observe that it is less effective in more diverse settings (e.g. multimodality) due to the varying granularity of each token and the…
Masked image modeling has been demonstrated as a powerful pretext task for generating robust representations that can be effectively generalized across multiple downstream tasks. Typically, this approach involves randomly masking patches…
Self-supervised learning for computer vision has achieved tremendous progress and improved many downstream vision tasks such as image classification, semantic segmentation, and object detection. Among these, generative self-supervised…
Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.…