More Like this

1. Learning Task Informed Abstractions

   Fu, Xiang; Yang, Ge; Agrawal, Pulkit; Jaakkola, Tommi (January 2021, Proceedings of the 38th International Conference on Machine Learning)

   null (Ed.)

   Current model-based reinforcement learning methods struggle when operating from complex visual scenes due to their inability to prioritize task-relevant features. To mitigate this prob- lem, we propose learning Task Informed Ab- stractions (TIA) that explicitly separates reward- correlated visual features from distractors. For learning TIA, we introduce the formalism of Task Informed MDP (TiMDP) that is realized by train- ing two models that learn visual features via coop- erative reconstruction, but one model is adversari- ally dissociated from the reward signal. Empirical evaluation shows that TIA leads to significant per- formance gains over state-of-the-art methods on many visual control tasks where natural and un- constrained visual distractions pose a formidable challenge. Project page: https://xiangfu.co/tia 

   more » « less
2. Natural Language Can Help Bridge the Sim2Real Gap

   Yu, Albert; Foote, Adeline; Mooney, Raymond; Martín-Martín, Roberto (June 2024, Robotics, Science and Systems (RSS))

   The main challenge in learning image-conditioned robotic policies is acquiring a visual representation conducive to low-level control. Due to the high dimensionality of the image space, learning a good visual representation requires a considerable amount of visual data. However, when learning in the real world, data is expensive. Sim2Real is a promising paradigm for overcoming data scarcity in the real-world target domain by using a simulator to collect large amounts of cheap data closely related to the target task. However, it is difficult to transfer an image-conditioned policy from sim to real when the domains are very visually dissimilar. To bridge the sim2real visual gap, we propose using natural language descriptions of images as a unifying signal across domains that captures the underlying task-relevant semantics. Our key insight is that if two image observations from different domains are labeled with similar language, the policy should predict similar action distributions for both images. We demonstrate that training the image encoder to predict the language description or the distance between descriptions of a sim or real image serves as a useful, data-efficient pretraining step that helps learn a domain-invariant image representation. We can then use this image encoder as the backbone of an IL policy trained simultaneously on a large amount of simulated and a handful of real demonstrations. Our approach outperforms widely used prior sim2real methods and strong vision-language pretraining baselines like CLIP and R3M by 25 to 40 percent. See additional videos and materials at our project website. 

   more » « less
3. Generative AI enables medical image segmentation in ultra low-data regimes

   https://doi.org/10.1038/s41467-025-61754-6  

   Zhang, Li; Jindal, Basu; Alaa, Ahmed; Weinreb, Robert; Wilson, David; Segal, Eran; Zou, James; Xie, Pengtao (July 2025, Nature Communications)

   Semantic segmentation of medical images is pivotal in applications like disease diagnosis and treatment planning. While deep learning automates this task effectively, it struggles in ultra low-data regimes for the scarcity of annotated segmentation masks. To address this, we propose a generative deep learning framework that produces high-quality image-mask pairs as auxiliary training data. Unlike traditional generative models that separate data generation from model training, ours uses multi-level optimization for end-to-end data generation. This allows segmentation performance to guide the generation process, producing data tailored to improve segmentation outcomes. Our method demonstrates strong generalization across 11 medical image segmentation tasks and 19 datasets, covering various diseases, organs, and modalities. It improves performance by 10–20% (absolute) in both same- and out-of-domain settings and requires 8–20 times less training data than existing approaches. This greatly enhances the feasibility and cost-effectiveness of deep learning in data-limited medical imaging scenarios. 

   more » « less
4. Cross-Modality Relevance for Reasoning on Language and Vision

   https://doi.org/10.18653/v1/2020.acl-main.683  

   Zheng, Chen; Guo, Quan; Kordjamshidi, Parisa (January 2020, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics)

   This work deals with the challenge of learning and reasoning over language and vision data for the related downstream tasks such as visual question answering (VQA) and natural language for visual reasoning (NLVR). We design a novel cross-modality relevance module that is used in an end-to-end framework to learn the relevance representation between components of various input modalities under the supervision of a target task, which is more generalizable to unobserved data compared to merely reshaping the original representation space. In addition to modeling the relevance between the textual entities and visual entities, we model the higher-order relevance between entity relations in the text and object relations in the image. Our proposed approach shows competitive performance on two different language and vision tasks using public benchmarks and improves the state-of-the-art published results. The learned alignments of input spaces and their relevance representations by NLVR task boost the training efficiency of VQA task. 

   more » « less
5. Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging

   Ruining Deng*, Can Cui* (July 2023, Medical Imaging with Deep Learning (MIDL))

   The segment anything model (SAM) was released as a foundation model for image segmentation. The promptable segmentation model was trained by over 1 billion masks on 11M licensed and privacy-respecting images. The model supports zero-shot image segmentation with various seg- mentation prompts (e.g., points, boxes, masks). It makes the SAM attractive for medical image analysis, especially for digital pathology where the training data are rare. In this study, we eval- uate the zero-shot segmentation performance of SAM model on representative segmentation tasks on whole slide imaging (WSI), including (1) tumor segmentation, (2) non-tumor tissue segmen- tation, (3) cell nuclei segmentation. Core Results: The results suggest that the zero-shot SAM model achieves remarkable segmentation performance for large connected objects. However, it does not consistently achieve satisfying performance for dense instance object segmentation, even with 20 prompts (clicks/boxes) on each image. We also summarized the identified limitations for digital pathology: (1) image resolution, (2) multiple scales, (3) prompt selection, and (4) model fine-tuning. In the future, the few-shot fine-tuning with images from downstream pathological seg- mentation tasks might help the model to achieve better performance in dense object segmentation. 

   more » « less