Related papers: RELO: Reinforcement Learning to Localize for Visua…

Tracking-by-detection approaches are some of the most successful object trackers in recent years. Their success is largely determined by the detector model they learn initially and then update over time. However, under challenging…

Many imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In…

The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotations…

Reinforcement learning (RL) for robot control typically requires a detailed representation of the environment state, including information about task-relevant objects not directly measurable. Keypoint detectors, such as spatial autoencoders…

The challenges to solving the collision avoidance problem lie in adaptively choosing optimal robot velocities in complex scenarios full of interactive obstacles. In this paper, we propose a distributed approach for multi-robot navigation…

Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To reduce the human labeling effort, we propose a novel webly…

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

This study proposes a semi-supervised co-training framework for object detection in densely packed retail environments, where limited labeled data and complex conditions pose major challenges. The framework combines Faster R-CNN (utilizing…

We present an active detection model for localizing objects in scenes. The model is class-specific and allows an agent to focus attention on candidate regions for identifying the correct location of a target object. This agent learns to…

Object detection involves two sub-tasks, i.e. localizing objects in an image and classifying them into various categories. For existing CNN-based detectors, we notice the widespread divergence between localization and classification, which…

Many continuous control tasks have easily formulated objectives, yet using them directly as a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many classical control tasks guide RL training using complex…

Most existing trackers based on discriminative correlation filters (DCF) try to introduce predefined regularization term to improve the learning of target objects, e.g., by suppressing background learning or by restricting change rate of…

Weakly supervised visual grounding aims to predict the region in an image that corresponds to a specific linguistic query, where the mapping between the target object and query is unknown in the training stage. The state-of-the-art method…

Behavioral cloning has proven to be effective for learning sequential decision-making policies from expert demonstrations. However, behavioral cloning often suffers from the causal confusion problem where a policy relies on the noticeable…

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

State-of-the-art visual recognition and detection systems increasingly rely on large amounts of training data and complex classifiers. Therefore it becomes increasingly expensive both to manually annotate datasets and to keep running times…

Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondence objectives. In this paper, we present Region-to-Object…

This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation…

To avoid myopic behavior, multi-step lookahead Bayesian optimization (BO) algorithms consider the sequential nature of BO and have demonstrated promising results in recent years. However, owing to the curse of dimensionality, most of these…

Landmark localization is a challenging problem in computer vision with a multitude of applications. Recent deep learning based methods have shown improved results by regressing likelihood maps instead of regressing the coordinates directly.…