Related papers: Progressive Transformation Learning for Leveraging…

Collecting operationally realistic data to inform machine learning models can be costly. Before collecting new data, it is helpful to understand where a model is deficient. For example, object detectors trained on images of rare objects may…

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…

Annotating bounding boxes is costly and limits the scalability of object detection. This challenge is compounded by the need to preserve high accuracy while minimizing manual effort in real-world applications. Prior active learning methods…

Temporal Action Localization (TAL) aims to detect the start and end timestamps of actions in a video. However, the training of TAL models requires a substantial amount of manually annotated data. Data programming is an efficient method to…

Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional…

Generative adversarial network (GAN) has greatly improved the quality of unsupervised image generation. Previous GAN-based methods often require a large amount of high-quality training data while producing a small number (e.g., tens) of…

The performance of modern object detectors drops when the test distribution differs from the training one. Most of the methods that address this focus on object appearance changes caused by, e.g., different illumination conditions, or gaps…

In this paper, we deal with the reality gap from a novel perspective, targeting transferring Deep Reinforcement Learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks. Instead of adopting…

Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment. While significant progress has been achieved with expensive LiDAR point clouds, it poses a great challenge for…

Model depth is a double-edged sword in deep learning: deeper models achieve higher accuracy but require higher computational cost. To efficiently train models at scale, an effective strategy is the progressive training, which scales up…

Adversarial attacks provide a good way to study the robustness of deep learning models. One category of methods in transfer-based black-box attack utilizes several image transformation operations to improve the transferability of…

The status quo approach to training object detectors requires expensive bounding box annotations. Our framework takes a markedly different direction: we transfer tracked object boxes from weakly-labeled videos to weakly-labeled images to…

Multi-task visual grounding (MTVG) includes two sub-tasks, i.e., Referring Expression Comprehension (REC) and Referring Expression Segmentation (RES). The existing representative approaches generally follow the research pipeline which…

We propose a new method for solving imaging inverse problems using text-to-image latent diffusion models as general priors. Existing methods using latent diffusion models for inverse problems typically rely on simple null text prompts,…

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In…

Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties with high spatial resolution. However, previous attempts to solve the optical inverse problem with supervised machine learning were…

Anatomical landmark segmentation and pathology localization are important steps in automated analysis of medical images. They are particularly challenging when the anatomy or pathology is small, as in retinal images and cardiac MRI, or when…

We propose a fully-convolutional conditional generative model, the latent transformation neural network (LTNN), capable of view synthesis using a light-weight neural network suited for real-time applications. In contrast to existing…

The objective of domain generalization (DG) is to enable models to be robust against domain shift. DG is crucial for deploying vision-language models (VLMs) in real-world applications, yet most existing methods rely on domain labels that…