Related papers: Dynamic Task and Weight Prioritization Curriculum …

Curriculum learning is a class of training strategies that organizes the data being exposed to a model by difficulty, gradually from simpler to more complex examples. This research explores a reverse curriculum generation approach that…

When faced with learning challenging new tasks, humans often follow sequences of steps that allow them to incrementally build up the necessary skills for performing these new tasks. However, in machine learning, models are most often…

Incorporating deep learning (DL) classification models into unmanned aerial vehicles (UAVs) can significantly augment search-and-rescue operations and disaster management efforts. In such critical situations, the UAV's ability to promptly…

Explainable deep learning models are advantageous in many situations. Prior work mostly provide unimodal explanations through post-hoc approaches not part of the original system design. Explanation mechanisms also ignore useful textual…

Multimedia content in social media platforms provides significant information during disaster events. The types of information shared include reports of injured or deceased people, infrastructure damage, and missing or found people, among…

Classification using multimodal data arises in many machine learning applications. It is crucial not only to model cross-modal relationship effectively but also to ensure robustness against loss of part of data or modalities. In this paper,…

Depth estimation models have shown promising performance on clear scenes but fail to generalize to adverse weather conditions due to illumination variations, weather particles, etc. In this paper, we propose WeatherDepth, a self-supervised…

Questions remain on the robustness of data-driven learning methods when crossing the gap from simulation to reality. We utilize weight anchoring, a method known from continual learning, to cultivate and fixate desired behavior in Neural…

We present a reward-predictive, model-based deep learning method featuring trajectory-constrained visual attention for local planning in visual navigation tasks. Our method learns to place visual attention at locations in latent image space…

Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance. Motivated by our insights from implicit curriculum…

Curriculum Learning (CL) is a meta-learning paradigm that trains a model by feeding the data instances incrementally according to a schedule, which is based on difficulty progression. Defining meaningful difficulty assessment measures is…

Multimodal models, such as the Contrastive Language-Image Pre-training (CLIP) model, have demonstrated remarkable success in aligning visual and linguistic representations. However, these models exhibit limitations when applied to…

Deep learning has shown successful application in visual recognition and certain artificial intelligence tasks. Deep learning is also considered as a powerful tool with high flexibility to approximate functions. In the present work,…

In the backdrop of increasing data requirements of Deep Neural Networks for object recognition that is growing more untenable by the day, we present Developmental PreTraining (DPT) as a possible solution. DPT is designed as a…

Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its…

Most previous deepfake detection methods bent their efforts to discriminate artifacts by end-to-end training. However, the learned networks often fail to mine the general face forgery information efficiently due to ignoring the data…

Curriculum learning (CL) mimics human learning, in which easy samples are learned first, followed by harder samples, and has become an effective method for training deep networks. However, many existing automatic CL methods maintain a…

Missing modalities have recently emerged as a critical research direction in multimodal emotion recognition (MER). Conventional approaches typically address this issue through missing modality reconstruction. However, these methods fail to…

Social networks can be a valuable source of information during crisis events. In particular, users can post a stream of multimodal data that can be critical for real-time humanitarian response. However, effectively extracting meaningful…

Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative…