相关论文: Domain-Adaptive Pretraining Improves Primate Behav…

Animal pose estimation (APE) aims to locate the animal body parts using a diverse array of sensor and modality inputs (e.g. RGB cameras, LiDAR, infrared, IMU, acoustic and language cues), which is crucial for research across neuroscience,…

Visual animal biometrics is rapidly gaining popularity as it enables a non-invasive and cost-effective approach for wildlife monitoring applications. Widespread usage of camera traps has led to large volumes of collected images, making…

Typically a classifier trained on a given dataset (source domain) does not performs well if it is tested on data acquired in a different setting (target domain). This is the problem that domain adaptation (DA) tries to overcome and, while…

Distributed Acoustic Sensing (DAS) technology finds growing applications across various domains. However, data distribution disparities due to heterogeneous sensing environments pose challenges for data-driven artificial intelligence (AI)…

Detecting facial action units (AU) is one of the fundamental steps in automatic recognition of facial expression of emotions and cognitive states. Though there have been a variety of approaches proposed for this task, most of these models…

Camera traps are used by ecologists globally as an efficient and non-invasive method to monitor animals. While it is time-consuming to manually label the collected images, recent advances in deep learning and computer vision has made it…

Animal pose estimation is challenging for existing image-based methods because of limited training data and large intra- and inter-species variances. Motivated by the progress of visual-language research, we propose that pre-trained…

Using drones to track multiple individuals simultaneously in their natural environment is a powerful approach for better understanding group primate behavior. Previous studies have demonstrated that it is possible to automate the…

Domain adaptive object detection aims to adapt detection models to domains where annotated data is unavailable. Existing methods have been proposed to address the domain gap using the semi-supervised student-teacher framework. However, a…

Automated animal censuses with aerial imagery are a vital ingredient towards wildlife conservation. Recent models are generally based on deep learning and thus require vast amounts of training data. Due to their scarcity and minuscule size,…

Gaining sustainable performance improvement with scaling data and model budget remains a pivotal yet unresolved challenge in autonomous driving. While autoregressive models exhibited promising data-scaling efficiency in planning tasks,…

Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining} (VEP), a method that learns generalizable representations…

Pre-training is a dominant paradigm in computer vision. For example, supervised ImageNet pre-training is commonly used to initialize the backbones of object detection and segmentation models. He et al., however, show a surprising result…

Pretraining with expert demonstrations have been found useful in speeding up the training process of deep reinforcement learning algorithms since less online simulation data is required. Some people use supervised learning to speed up the…

This paper addresses domain adaptation for the pixel-wise classification of remotely sensed data using deep neural networks (DNN) as a strategy to reduce the requirements of DNN with respect to the availability of training data. We focus on…

Quantification of behavior is critical in applications ranging from neuroscience, veterinary medicine and animal conservation efforts. A common key step for behavioral analysis is first extracting relevant keypoints on animals, known as…

While Reinforcement Learning (RL) agents can successfully learn to handle complex tasks, effectively generalizing acquired skills to unfamiliar settings remains a challenge. One of the reasons behind this is the visual encoders used are…

The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper, we propose…

This article proposes a novel approach for augmenting generative adversarial network (GAN) with a self-supervised task in order to improve its ability for encoding video representations that are useful in downstream tasks such as human…

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data,…