相关论文: Adaptive Data Selection for Multi-Layer Perceptron…

In this paper we investigate image classification with computational resource limits at test time. Two such settings are: 1. anytime classification, where the network's prediction for a test example is progressively updated, facilitating…

Apart from discriminative models for classification and object detection tasks, the application of deep convolutional neural networks to basic research utilizing natural imaging data has been somewhat limited; particularly in cases where a…

The support vector machines (SVM) is one of the most widely used and practical optimization based classification models in machine learning because of its interpretability and flexibility to produce high quality results. However, the big…

Big data, i.e. collecting, storing and processing of data at scale, has recently been possible due to the arrival of clusters of commodity computers powered by application-level distributed parallel operating systems like HDFS/Hadoop/Spark,…

Machine learning techniques face numerous challenges to achieve optimal performance. These include computational constraints, the limitations of single-view learning algorithms and the complexity of processing large datasets from different…

Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system.…

In some practical learning tasks, such as traffic video analysis, the number of available training samples is restricted by different factors, such as limited communication bandwidth and computation power. Determinantal Point Process (DPP)…

Time-aware data valuation enhances training efficiency and model robustness, as early detection of harmful samples could prevent months of wasted computation. However, existing methods rely on model retraining or convergence assumptions or…

Convolutional Neural Networks (CNNs) were recently shown to provide state-of-the-art results for object category viewpoint estimation. However different ways of formulating this problem have been proposed and the competing approaches have…

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…

While several convolution-like operators have recently been proposed for extracting features out of point clouds, down-sampling an unordered point cloud in a deep neural network has not been rigorously studied. Existing methods down-sample…

The paradigm shift from shallow classifiers with hand-crafted features to end-to-end trainable deep learning models has shown significant improvements on supervised learning tasks. Despite the promising power of deep neural networks (DNN),…

The performance of video prediction has been greatly boosted by advanced deep neural networks. However, most of the current methods suffer from large model sizes and require extra inputs, e.g., semantic/depth maps, for promising…

Attributing model behavior to training data is an evolving research field. A common benchmark is data removal, which involves eliminating data instances with either low or high values, then assessing a model's performance trained on the…

As the right to be forgotten becomes legislated worldwide, machine unlearning mechanisms have emerged to efficiently update models for data deletion and enhance user privacy protection. However, existing machine unlearning algorithms…

Different from large-scale platforms such as Taobao and Amazon, CVR modeling in small-scale recommendation scenarios is more challenging due to the severe Data Distribution Fluctuation (DDF) issue. DDF prevents existing CVR models from…

Instruction tuning fine-tunes pre-trained Multi-modal Large Language Models (MLLMs) to handle real-world tasks. However, the rapid expansion of visual instruction datasets introduces data redundancy, leading to excessive computational…

We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DRConv outperforms…

Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability…

While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often infeasible due to computational constraints and…