Related papers: DAP: Detection-Aware Pre-training with Weak Superv…
Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised…
Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial…
Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…
Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a…
Anomaly activities such as robbery, explosion, accidents, etc. need immediate actions for preventing loss of human life and property in real world surveillance systems. Although the recent automation in surveillance systems are capable of…
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…
Dropout Variational Inference, or Dropout Sampling, has been recently proposed as an approximation technique for Bayesian Deep Learning and evaluated for image classification and regression tasks. This paper investigates the utility of…
Training deep object detectors demands expensive bounding box annotation. Active learning (AL) is a promising technique to alleviate the annotation burden. Performing AL at box-level for object detection, i.e., selecting the most…
Surface defect detection plays a critical role in industrial quality inspection. Recent advances in artificial intelligence have significantly enhanced the automation level of detection processes. However, conventional semantic segmentation…
Automatic road extraction from satellite imagery using deep learning is a viable alternative to traditional manual mapping. Therefore it has received considerable attention recently. However, most of the existing methods are supervised and…
Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data…
Recently,the detection transformer has gained substantial attention for its inherent minimal post-processing requirement.However,this paradigm relies on abundant training data,yet in the context of the cross-domain adaptation,insufficient…
Weakly supervised object localization (WSOL) focuses on localizing objects only with the supervision of image-level classification masks. Most previous WSOL methods follow the classification activation map (CAM) that localizes objects based…
The high cost of pixel-level annotations makes it appealing to train saliency detection models with weak supervision. However, a single weak supervision source usually does not contain enough information to train a well-performing model. To…
Training a Convolutional Neural Network (CNN) for semantic segmentation typically requires to collect a large amount of accurate pixel-level annotations, a hard and expensive task. In contrast, simple image tags are easier to gather. With…
Prompt tuning (PT), as an emerging resource-efficient fine-tuning paradigm, has showcased remarkable effectiveness in improving the task-specific transferability of vision-language models. This paper delves into a previously overlooked…
Deep learning based salient object detection has recently achieved great success with its performance greatly outperforms any other unsupervised methods. However, annotating per-pixel saliency masks is a tedious and inefficient procedure.…
Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent. While these methods have achieved successes in various…
Deep neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal importance and determining the activity relevance of…
Few-shot classification studies the problem of quickly adapting a deep learner to understanding novel classes based on few support images. In this context, recent research efforts have been aimed at designing more and more complex…