Search Results for author:
Found 49 papers, 10 papers with code
Overcoming catastrophic forgetting through weight consolidation and long-term memory
We obtain similar results with a much more difficult disjoint CIFAR10 task (70. 10% initial task 1 performance, 67. 73% after learning tasks 2 and 3 for AD+EWC, while PGD and EWC both fall to chance level).
EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
Finally, the third component creates a large-scale pseudo-labeled instance segmentation training dataset by compositing the foreground object masks onto the original and generated background images.
Improving Zero-shot Generalization and Robustness of Multi-modal Models
We also show that our method improves across ImageNet shifted datasets and other model architectures such as LiT.
Supervised Contrastive Prototype Learning: Augmentation Free Robust Neural Network
Inspired by the recent success of prototypical and contrastive learning frameworks for both improving robustness and learning nuance invariant representations, we propose a training framework, $\textbf{Supervised Contrastive Prototype Learning}$ (SCPL).
Neural-Sim: Learning to Generate Training Data with NeRF
However, existing approaches either require human experts to manually tune each scene property or use automatic methods that provide little to no control; this requires rendering large amounts of random data variations, which is slow and is often suboptimal for the target domain.
Contributions of Shape, Texture, and Color in Visual Recognition
We use human experiments to confirm that both HVE and humans predominantly use some specific features to support the classification of specific classes (e. g., texture is the dominant feature to distinguish a zebra from other quadrupeds, both for humans and HVE).
DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection
For foreground object mask generation, we use a simple textual template with object class name as input to DALL-E to generate a diverse set of foreground images.
Invariant Structure Learning for Better Generalization and Causal Explainability
ISL splits the data into different environments, and learns a structure that is invariant to the target across different environments by imposing a consistency constraint.
Model2Detector:Widening the Information Bottleneck for Out-of-Distribution Detection using a Handful of Gradient Steps
Our work can be employed as a post-processing method whereby an inference-time ML system can convert a trained model into an OOD detector.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
What can we learn from misclassified ImageNet images?
Hence, we propose a two-stage Super-Sub framework, and demonstrate that: (i) The framework improves overall classification performance by 3. 3%, by first inferring a superclass using a generalist superclass-level network, and then using a specialized network for final subclass-level classification.
Encouraging Disentangled and Convex Representation with Controllable Interpolation Regularization
(2) They lack convexity constraints, which is important for meaningfully manipulating specific attributes for downstream tasks.
GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL
Extending the successes in supervised learning methods to the reinforcement learning (RL) setting, however, is difficult due to the data generating process - RL agents actively query their environment for data, and the data are a function of the policy followed by the agent.
Out of Distribution (OOD) Detection
Reinforcement Learning (RL)
Towards Generic Interface for Human-Neural Network Knowledge Exchange
Take image classification as an example, HNI visualizes the reasoning logic of a NN with class-specific Structural Concept Graphs (c-SCG), which are human-interpretable.
Video2Skill: Adapting Events in Demonstration Videos to Skills in an Environment using Cyclic MDP Homomorphisms
Humans excel at learning long-horizon tasks from demonstrations augmented with textual commentary, as evidenced by the burgeoning popularity of tutorial videos online.
Shaped Policy Search for Evolutionary Strategies using Waypoints
In this paper, we try to improve exploration in Blackbox methods, particularly Evolution strategies (ES), when applied to Reinforcement Learning (RL) problems where intermediate waypoints/subgoals are available.
A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts
Despite substantial progress in applying neural networks (NN) to a wide variety of areas, they still largely suffer from a lack of transparency and interpretability.
Graph Autoencoder for Graph Compression and Representation Learning
We consider the problem of graph data compression and representation.
Generative Auto-Encoder: Non-adversarial Controllable Synthesis with Disentangled Exploration
DEAE can become a generative model and synthesis semantic controllable samples by interpolating latent code, which can even synthesis novel attribute value never is shown in the original dataset.
Lifelong Learning Without a Task Oracle
Supervised deep neural networks are known to undergo a sharp decline in the accuracy of older tasks when new tasks are learned, termed "catastrophic forgetting".
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
Inspired by this, we attempt to equip reinforcement learning agents with the ability to perform experiments that facilitate a categorization of the rolled-out trajectories, and to subsequently infer the causal factors of the environment in a hierarchical manner.
SHERLock: Self-Supervised Hierarchical Event Representation Learning
Also, they are believed to be arranged hierarchically, allowing for an efficient representation of complex long-horizon experiences.
Beneficial Perturbation Network for designing general adaptive artificial intelligence systems
Continual learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby a previously learned mapping of an old task is erased when learning new mappings for new tasks.
Beneficial Perturbations Network for Defending Adversarial Examples
The reason is that neural networks fail to accommodate the distribution drift of the input data caused by adversarial perturbations.
Zero-shot Synthesis with Group-Supervised Learning
Visual cognition of primates is superior to that of artificial neural networks in its ability to 'envision' a visual object, even a newly-introduced one, in different attributes including pose, position, color, texture, etc.
Attentive Feature Reuse for Multi Task Meta learning
Our method improves performance on new, previously unseen environments, and is 1. 5x faster than standard existing meta learning methods using similar architectures.
Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition
After training on unbalanced discrete poses (5 classes with 6 poses per object instance, plus 5 classes with only 2 poses), we show that OPT-Net can synthesize balanced continuous new poses along yaw and pitch axes with high quality.
Meta Adaptation using Importance Weighted Demonstrations
Imitation learning has gained immense popularity because of its high sample-efficiency.
Adversarial Training: embedding adversarial perturbations into the parameter space of a neural network to build a robust system
Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks.
Learning Causal State Representations of Partially Observable Environments
In this paper, we propose an algorithm to approximate causal states, which are the coarsest partition of the joint history of actions and observations in partially-observable Markov decision processes (POMDP).
Beneficial perturbation network for continual learning
Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge.
Closed-Loop Memory GAN for Continual Learning
Sequential learning of tasks using gradient descent leads to an unremitting decline in the accuracy of tasks for which training data is no longer available, termed catastrophic forgetting.
Overcoming catastrophic forgetting problem by weight consolidation and long-term memory
We apply our method to sequentially learning to classify digits 0, 1, 2 (task 1), 4, 5, 6, (task 2), and 7, 8, 9 (task 3) in MNIST (disjoint MNIST task).
Born Again Neural Networks
Knowledge distillation (KD) consists of transferring knowledge from one machine learning model (the teacher}) to another (the student).
Learning to Recognize Objects by Retaining other Factors of Variation
We show that disCNN achieves significantly better object recognition accuracies than AlexNet trained solely to predict object categories on the iLab-20M dataset, which is a large scale turntable dataset with detailed object pose and lighting information.
Improved Deep Learning of Object Category using Pose Information
Further more, we fine-tune object recognition on ImageNet by using the pretrained 2W-CNN and AlexNet features on iLab-20M, results show that significant improvements have been achieved, compared with training AlexNet from scratch.
metricDTW: local distance metric learning in Dynamic Time Warping
We propose to learn multiple local Mahalanobis distance metrics to perform k-nearest neighbor (kNN) classification of temporal sequences.
Active Long Term Memory Networks
Continual Learning in artificial neural networks suffers from interference and forgetting when different tasks are learned sequentially.
shapeDTW: shape Dynamic Time Warping
Dynamic Time Warping (DTW) is an algorithm to align temporal sequences with possible local non-linear distortions, and has been widely applied to audio, video and graphics data alignments.
iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning
Tolerance to image variations (e. g. translation, scale, pose, illumination, background) is an important desired property of any object recognition system, be it human or machine.
Detecting "Smart" Spammers On Social Network: A Topic Model Approach
Spammer detection on social network is a challenging problem.
What can we learn about CNNs from a large scale controlled object dataset?
Tolerance to image variations (e. g. translation, scale, pose, illumination) is an important desired property of any object recognition system, be it human or machine.
Computational models: Bottom-up and top-down aspects
We focus on {\em computational models of attention} as defined by Tsotsos \& Rothenstein \shortcite{Tsotsos_Rothenstein11}: Models which can process any visual stimulus (typically, an image or video clip), which can possibly also be given some task definition, and which make predictions that can be compared to human or animal behavioral or physiological responses elicited by the same stimulus and task.
Computational models of attention
This chapter reviews recent computational models of visual attention.
Fixation Bank: Learning to Reweight Fixation Candidates
Predicting where humans will fixate in a scene has many practical applications.
CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research
Saliency modeling has been an active research area in computer vision for about two decades.
Human vs. Computer in Scene and Object Recognition
Several decades of research in computer and primate vision have resulted in many models (some specialized for one problem, others more general) and invaluable experimental data.
Bayesian optimization explains human active search
Many real-world problems have complicated objective functions.
6th International Symposium on Attention in Cognitive Systems 2013
This volume contains the papers accepted at the 6th International Symposium on Attention in Cognitive Systems (ISACS 2013), held in Beijing, August 5, 2013.
