Search Results for author:
Found 33 papers, 11 papers with code
Learning Imbalanced Datasets with Maximum Margin Loss
A learning algorithm referred to as Maximum Margin (MM) is proposed for considering the class-imbalance data learning issue: the trained model tends to predict the majority of classes rather than the minority ones.
How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning
This yields a unified perspective on how negative samples and SimSiam alleviate collapse.
Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo
Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior because the negative sample size (NSS) is limited by its mini-batch size (MBS).
SoftGroup for 3D Instance Segmentation on Point Clouds
The hard predictions are made when performing semantic segmentation such that each point is associated with a single class.
Ranked #1 on
3D Instance Segmentation
on STPLS3D
Noise Augmentation Is All You Need For FGSM Fast Adversarial Training: Catastrophic Overfitting And Robust Overfitting Require Different Augmentation
Adversarial training (AT) and its variants are the most effective approaches for obtaining adversarially robust models.
GDCA: GAN-based single image super resolution with Dual discriminators and Channel Attention
Single Image Super-Resolution (SISR) is a very active research field.
Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment
The actual sampling for large TD error is performed in two steps: first, an episode is sampled from the relay buffer according to the average TD error of its experiences, and then, for the sampled episode, the hindsight goal leading to larger TD error is sampled with higher probability from future visited states.
How Does SimSiam Avoid Collapse Without Negative Samples? Towards a Unified Understanding of Progress in SSL
Towards avoiding collapse in self-supervised learning (SSL), contrastive loss is widely used but often requires a large number of negative samples.
Active Learning: Sampling in the Least Probable Disagreement Region
This strategy is valid only when the sample's "closeness" to the decision boundary can be estimated.
LEARNING PHONEME-LEVEL DISCRETE SPEECH REPRESENTATION WITH WORD-LEVEL SUPERVISION
Phonemes are defined by their relationship to words: changing a phoneme changes the word.
Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold
This paper defines fair principal component analysis (PCA) as minimizing the maximum mean discrepancy (MMD) between dimensionality-reduced conditional distributions of different protected classes.
Self-supervised Learning with Local Attention-Aware Feature
In this work, we propose a novel methodology for self-supervised learning for generating global and local attention-aware visual features.
Structured Co-reference Graph Attention for Video-grounded Dialogue
A video-grounded dialogue system referred to as the Structured Co-reference Graph Attention (SCGA) is presented for decoding the answer sequence to a question regarding a given video while keeping track of the dialogue context.
Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm that provides good weight initialization of a model given a variety of learning tasks.
Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model
Developing an agent in reinforcement learning (RL) that is capable of performing complex control tasks directly from high-dimensional observation such as raw pixels is yet a challenge as efforts are made towards improving sample efficiency and generalization.
Semantic Grouping Network for Video Captioning
This paper considers a video caption generating network referred to as Semantic Grouping Network (SGN) that attempts (1) to group video frames with discriminating word phrases of partially decoded caption and then (2) to decode those semantically aligned groups in predicting the next word.
Least Probable Disagreement Region for Active Learning
Active learning strategy to query unlabeled samples nearer the estimated decision boundary at each step has been known to be effective when the distance from the sample data to the decision boundary can be explicitly evaluated; however, in numerous cases in machine learning, especially when it involves deep learning, conventional distance such as the $\ell_p$ from sample to decision boundary is not readily measurable.
SCNet: Training Inference Sample Consistency for Instance Segmentation
This paper proposes an architecture referred to as Sample Consistency Network (SCNet) to ensure that the IoU distribution of the samples at training time is close to that at inference time.
VLANet: Video-Language Alignment Network for Weakly-Supervised Video Moment Retrieval
This paper explores methods for performing VMR in a weakly-supervised manner (wVMR): training is performed without temporal moment labels but only with the text query that describes a segment of the video.
Modality Shifting Attention Network for Multi-modal Video Question Answering
To this end, MSAN is based on (1) the moment proposal network (MPN) that attempts to locate the most appropriate temporal moment from each of the modalities, and also on (2) the heterogeneous reasoning network (HRN) that predicts the answer using an attention mechanism on both modalities.
Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution
This paper considers an architecture referred to as Cascade Region Proposal Network (Cascade RPN) for improving the region-proposal quality and detection performance by \textit{systematically} addressing the limitation of the conventional RPN that \textit{heuristically defines} the anchors and \textit{aligns} the features to the anchors.
Ranked #154 on
Object Detection
on COCO test-dev
(using extra training data)
Gaining Extra Supervision via Multi-task learning for Multi-Modal Video Question Answering
This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering.
Edge-labeling Graph Neural Network for Few-shot Learning
In this paper, we propose a novel edge-labeling graph neural network (EGNN), which adapts a deep neural network on the edge-labeling graph, for few-shot learning.
Learning to Augment Influential Data
The differentiable augmentation model and reformulation of the influence function allow the parameters of the augmented model to be directly updated by backpropagation to minimize the validation loss.
Progressive Attention Memory Network for Movie Story Question Answering
To overcome these challenges, PAMN involves three main features: (1) progressive attention mechanism that utilizes cues from both question and answer to progressively prune out irrelevant temporal parts in memory, (2) dynamic modality fusion that adaptively determines the contribution of each modality for answering the current question, and (3) belief correction answering scheme that successively corrects the prediction score on each candidate answer.
Ranked #1 on
Video Story QA
on MovieQA
Fast and Efficient Image Quality Enhancement via Desubpixel Convolutional Neural Networks
This paper considers a convolutional neural network for image quality enhancement referred to as the fast and efficient quality enhancement (FEQE) that can be trained for either image super-resolution or image enhancement to provide accurate yet visually pleasing images on mobile devices by addressing the following three main issues.
Pivot Correlational Neural Network for Multimodal Video Categorization
The architecture is trained to maximizes the correlation between the hidden states as well as the predictions of the modal-agnostic pivot stream and modal-specific stream in the network.
A Resizable Mini-batch Gradient Descent based on a Multi-Armed Bandit
Determining the appropriate batch size for mini-batch gradient descent is always time consuming as it often relies on grid search.
Meta-Learning via Feature-Label Memory Network
The feature memory is used to store the features of input data samples and the label memory stores their labels.
Early Improving Recurrent Elastic Highway Network
Expanding on the idea of adaptive computation time (ACT), with the use of an elastic gate in the form of a rectified exponentially decreasing function taking on as arguments as previous hidden state and input, the proposed model is able to evaluate the appropriate recurrent depth for each input.
Face Alignment Using Cascade Gaussian Process Regression Trees
Without increasing prediction time, the prediction of cGPRT can be performed in the same framework as the cascade regression trees (CRT) but with better generalization.
Phoneme Classification using Constrained Variational Gaussian Process Dynamical System
This paper describes a new acoustic model based on variational Gaussian process dynamical system (VGPDS) for phoneme classification.
Higher-Order Correlation Clustering for Image Segmentation
For many of the state-of-the-art computer vision algorithms, image segmentation is an important preprocessing step.
