Related papers: A Controller-Recognizer Framework: How necessary i…

The use of explicit object detectors as an intermediate step to image captioning - which used to constitute an essential stage in early work - is often bypassed in the currently dominant end-to-end approaches, where the language model is…

Visual recognition systems mounted on autonomous moving agents face the challenge of unconstrained data, but simultaneously have the opportunity to improve their performance by moving to acquire new views of test data. In this work, we…

Visual Commonsense Reasoning (VCR) remains a significant yet challenging research problem in the realm of visual reasoning. A VCR model generally aims at answering a textual question regarding an image, followed by the rationale prediction…

For humans, object detection, recognition, and tracking are innate. These provide the ability for human to perceive their environment and objects within their environment. This ability however doesn't translate well in computers. In…

The topic of provable deep neural network robustness has raised considerable interest in recent years. Most research has focused on adversarial robustness, which studies the robustness of perceptive models in the neighbourhood of particular…

Learning-based congestion controllers offer better adaptability compared to traditional heuristics. However, the unreliability of learning techniques can cause learning-based controllers to behave poorly, creating a need for formal…

Autonomous systems are increasingly implemented using end-to-end learning-based controllers. Such controllers make decisions that are executed on the real system, with images as one of the primary sensing modalities. Deep neural networks…

Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a…

Camera control is crucial for generating expressive and cinematic videos. Existing methods rely on explicit sequences of camera parameters as control conditions, which can be cumbersome for users to construct, particularly for intricate…

Soft-reset controllers are introduced as a way to approximate hard-reset controllers. The focus is on implementing reset controllers that are (strictly) passive and on analyzing their interconnection with passive plants. A passive…

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

For multiple scientific endeavors it is common to measure a phenomenon of interest in more than one ways. We make observations of objects from several different perspectives in space, at different points in time; we may also measure…

Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-identification is considered. Attention mechanisms have…

Contrastive Learning (CL) has emerged as a powerful method for training feature extraction models using unlabeled data. Recent studies suggest that incorporating a linear projection head post-backbone significantly enhances model…

Computer vision is developing rapidly with the support of deep learning techniques. This thesis proposes an advanced vehicle-detection model based on an improvement to classical convolutional neural networks. The advanced model was applied…

We consider artificial agents that learn to jointly control their gripperand camera in order to reinforcement learn manipulation policies in the presenceof occlusions from distractor objects. Distractors often occlude the object of…

To tackle interpretability in deep learning, we present a novel framework to jointly learn a predictive model and its associated interpretation model. The interpreter provides both local and global interpretability about the predictive…

We present a neural rendering framework that maps a voxelized scene into a high quality image. Highly-textured objects and scene element interactions are realistically rendered by our method, despite having a rough representation as an…

Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the…

We study active object tracking, where a tracker takes visual observations (i.e., frame sequences) as input and produces the corresponding camera control signals as output (e.g., move forward, turn left, etc.). Conventional methods tackle…